CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Cortex

abbacusgroup/cortex
1530 toolsSTDIOregistry active
Summary

This is a local knowledge base with semantic reasoning built in. It captures decisions, fixes, lessons, and research into an RDF graph with an OWL-RL ontology, then runs entity extraction, relationship inference, and hybrid retrieval over them. The 22 MCP tools cover search, context briefings, entity dossiers, graph queries, and pipeline controls. It runs as a single HTTP server that owns the graph store, so your CLI, dashboard, and Claude Desktop all hit the same data. Install spins up background services on macOS and Linux. Useful if you want persistent memory across conversations with automatic classification and reasoning, or if you're building an agent that needs to accumulate structured knowledge over time.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Tools

Public tool metadata for what this MCP can expose to an agent.

30 tools
listAllEntitiesList and filter catalog entities with support for pagination, search, and various filters including groups, types, owners, and git repositories. If the client is trying to fetch data for teams, use 'type': 'team' in these APIs.16 params

List and filter catalog entities with support for pagination, search, and various filters including groups, types, owners, and git repositories. If the client is trying to fetch data for teams, use 'type': 'team' in these APIs.

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
querystring
Filter based on a [search query](https://docs.cortex.io/settings/search). This will search across entity properties. If provided, results will be sorted by relevance.default:
typesarray
Filter the response to specific types of entities. By default, this includes services, resources, and domains. Corresponds to the `x-cortex-type` field in the entity descriptor.
groupsarray
Filter based on groups, which correspond to the `x-cortex-groups` field in the Catalog Descriptor. Accepts a comma-delimited list of groups
ownersarray
Filter based on owner group names, which correspond to the `x-cortex-owners` field in the Catalog Descriptor. Accepts a comma-delimited list of owner group names
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
includeLinksboolean
Whether to include links for each entity in the responsedefault: false
includeOwnersboolean
Whether to include ownership information for each entity in the responsedefault: false
hierarchyDepthstring
Depth of the parent / children hierarchy nodes. Can be 'full' or a valid integerdefault: full
gitRepositoriesarray
Supports only GitHub repositories in the `org/repo` format
includeArchivedboolean
Whether to include archived entities in the responsedefault: false
includeMetadataboolean
Whether to include custom data for each entity in the responsedefault: false
includeNestedFieldsarray
List of sub fields to include for different types
includeSlackChannelsboolean
Whether to include Slack channels for each entity in the response
includeHierarchyFieldsarray
List of sub fields to include for hierarchies. Only supports 'groups'
listEntityDescriptorsCortex Catalog API - Access and manage your service catalog, teams, domains, and resources5 params

Cortex Catalog API - Access and manage your service catalog, teams, domains, and resources

Parameters* required
pageinteger
Page number to return, 0 indexed
yamlboolean
When true, returns the YAML representation of the descriptors
typesarray
Filter the response to specific types of entities. By default, this includes services, resources, and domains. Corresponds to the `x-cortex-type` field in the entity descriptor.
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
pageSizeinteger
Number of entities to return per page
listDependenciesForEntityList all dependencies for an entity including both incoming (who depends on this service) and outgoing (what this service depends on) relationships. Essential for understanding service interactions, planning changes, and assessing blast radius6 params

List all dependencies for an entity including both incoming (who depends on this service) and outgoing (what this service depends on) relationships. Essential for understanding service interactions, planning changes, and assessing blast radius

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
callerTagstring
includeIncomingboolean
default: false
includeOutgoingboolean
default: true
getDependencyGet specific dependency details between two entities including method, path, and metadata. Useful for understanding the nature of the relationship, API contracts, and communication patterns between services5 params

Get specific dependency details between two entities including method, path, and metadata. Useful for understanding the nature of the relationship, API contracts, and communication patterns between services

Parameters* required
pathstring
methodstring
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
calleeTagstring
callerTagstring
getEntityDetailsRetrieve comprehensive details about a specific entity including its metadata, ownership, hierarchies, and relationships. This is the primary method for getting complete information about services, teams, or domains.5 params

Retrieve comprehensive details about a specific entity including its metadata, ownership, hierarchies, and relationships. This is the primary method for getting complete information about services, teams, or domains.

Parameters* required
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
includeOwnersboolean
Include ownership information, default is true
hierarchyDepthstring
Depth of the parent / children hierarchy nodes. Can be 'full' or a valid integerdefault: full
includeHierarchyFieldsarray
List of sub fields to include for hierarchies. Only supports 'groups'
getCustomDataForEntityList all custom data key-value pairs associated with an entity. Retrieve metadata, configuration settings, and custom attributes stored for services, resources, or domains. Supports pagination for entities with large amounts of custom data4 params

List all custom data key-value pairs associated with an entity. Retrieve metadata, configuration settings, and custom attributes stored for services, resources, or domains. Supports pagination for entities with large amounts of custom data

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
getCustomDataForEntityByKeyRetrieve a specific custom data value by key for an entity. Efficiently access individual metadata attributes, configuration values, or custom properties without fetching all custom data3 params

Retrieve a specific custom data value by key for an entity. Efficiently access individual metadata attributes, configuration values, or custom properties without fetching all custom data

Parameters* required
keystring
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
listCustomEventsForEntityList custom events for an entity with optional filtering by type and time range. Supports pagination and filtering by event type, start time, and end time to retrieve historical event data8 params

List custom events for an entity with optional filtering by type and time range. Supports pagination and filtering by event type, start time, and end time to retrieve historical event data

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
typestring
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
endTimestring
If provided, events with less than or equal to timestamp will be returned (a date-time without a time-zone in the ISO-8601 calendar system)
tagOrIdstring
Entity identifier - can be a tag or CID
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
startTimestring
If provided, events with greater than or equal to timestamp will be returned (a date-time without a time-zone in the ISO-8601 calendar system)
timestampstring
Use 'startTime' instead
getCustomEventForEntityByUuidRetrieve a specific custom event by its UUID. Returns event details including title, description, timestamp, type, and any custom data associated with the event3 params

Retrieve a specific custom event by its UUID. Returns event details including title, description, timestamp, type, and any custom data associated with the event

Parameters* required
uuidstring
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
getDeploysForEntityList all deployments for a specific catalog entity. Returns deployment history including timestamps, environments, SHAs, and deployment types in paginated format4 params

List all deployments for a specific catalog entity. Returns deployment history including timestamps, environments, SHAs, and deployment types in paginated format

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
getCurrentOncallForEntityRetrieve the current on-call personnel for an entity in real-time. Shows who is actively responsible for incident response, including primary and secondary on-call, contact information, and rotation schedules2 params

Retrieve the current on-call personnel for an entity in real-time. Shows who is actively responsible for incident response, including primary and secondary on-call, contact information, and rotation schedules

Parameters* required
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
getEntityDescriptorCortex Catalog API - Access and manage your service catalog, teams, domains, and resources3 params

Cortex Catalog API - Access and manage your service catalog, teams, domains, and resources

Parameters* required
yamlboolean
When true, returns the YAML representation of the descriptor
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
listEntityDestinationsForRelationshipTypeList all destinations for a certain relationship type & entity. Use the listRelationshipTypes tool to find the relevant relationshipTypeTag.5 params

List all destinations for a certain relationship type & entity. Use the listRelationshipTypes tool to find the relevant relationshipTypeTag.

Parameters* required
depthstring
Maximum depth to traverse in the relationship hierarchy. Defaults to 1 (i.e., direct relationships only).
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
includeArchivedboolean
If true will include relationships that traverse archived entitiesdefault: false
relationshipTypeTagstring
listEntitySourcesForRelationshipTypeList all sources for a certain relationship type & entity. Use the listRelationshipTypes tool to find the relevant relationshipTypeTag.5 params

List all sources for a certain relationship type & entity. Use the listRelationshipTypes tool to find the relevant relationshipTypeTag.

Parameters* required
depthstring
Maximum depth to traverse in the relationship hierarchy. Defaults to 1 (i.e., direct relationships only).
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
includeArchivedboolean
If true will include relationships that traverse archived entitiesdefault: false
relationshipTypeTagstring
getCustomMetricDataRetrieve custom metric data points for an entity. Returns paginated time-series data for a specific custom metric, with optional filtering by date range to analyze trends and patterns7 params

Retrieve custom metric data points for an entity. Returns paginated time-series data for a specific custom metric, with optional filtering by date range to analyze trends and patterns

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
endDatestring
End date for the filter (inclusive)
tagOrIdstring
Entity identifier - can be a tag or CID
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
startDatestring
Start date for the filter (inclusive). Default: 6 months
customMetricKeystring
Key for the custom metric filter
queryPointInTimeMetricsExecute point-in-time queries for one or more engineering metrics. Returns current metric values for specified time periods, with support for batch queries and optional period-over-period comparisons. Time range (startTime/endTime) cannot exceed 6 months (180 days). PREREQUISI...14 params

Execute point-in-time queries for one or more engineering metrics. Returns current metric values for specified time periods, with support for batch queries and optional period-over-period comparisons. Time range (startTime/endTime) cannot exceed 6 months (180 days). PREREQUISI...

Parameters* required
limitinteger
Maximum number of results to return
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
endTimestring
End time for the query period
filtersarray
Filters to apply to the data
groupByarray
Fields to group results by
metricsarray
List of metrics to query with their aggregation functions
orderByarray
Sort order for results
nextPagestring
Pagination token for next page of results
startTimestring
Start time for the query period
comparisonvalue
nestedGroupByarray
Fields to group nested results by
nestedMetricsarray
Optional nested metrics for advanced queries
timeAttributestring
Time attribute to use for queries
nestedTimeAttributestring
Time attribute for nested queries
listMetricDefinitionsList all available engineering metric definitions. USAGE - Call this endpoint BEFORE querying metrics (queryPointInTimeMetrics): 1. Once at start: Call with view='basic' to discover all available metrics - cache this response 2. Once per metric: Call with view='full' and key=M...3 params

List all available engineering metric definitions. USAGE - Call this endpoint BEFORE querying metrics (queryPointInTimeMetrics): 1. Once at start: Call with view='basic' to discover all available metrics - cache this response 2. Once per metric: Call with view='full' and key=M...

Parameters* required
keyarray
viewstring
default: basic
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
listInitiativesList all initiatives in the organization with optional filters for draft and expired initiatives. View active improvement programs, strategic projects, and their current status to understand organizational priorities and track progress5 params

List all initiatives in the organization with optional filters for draft and expired initiatives. View active improvement programs, strategic projects, and their current status to understand organizational priorities and track progress

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
includeDraftsboolean
Whether or not to include draft Initiatives in the responsedefault: false
includeExpiredboolean
Whether or not to include expired Initiatives in the responsedefault: false
getInitiativeRetrieve detailed information about a specific initiative including its goals, timeline, affected entities, scorecard targets, and current progress. Essential for understanding initiative scope and tracking achievement of objectives2 params

Retrieve detailed information about a specific initiative including its goals, timeline, affected entities, scorecard targets, and current progress. Essential for understanding initiative scope and tracking achievement of objectives

Parameters* required
cidstring
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
getMyWorkspaceTOOL for retrieving current user's owned resources and work items across the Cortex workspace. FLEXIBLE REQUEST STRUCTURE: The request accepts an object with optional fields for each resource type: - myEntitiesRequest: Fetch entities (services, resources, domains) owned by the...7 params

TOOL for retrieving current user's owned resources and work items across the Cortex workspace. FLEXIBLE REQUEST STRUCTURE: The request accepts an object with optional fields for each resource type: - myEntitiesRequest: Fetch entities (services, resources, domains) owned by the...

Parameters* required
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
myTeamsRequestobject
Request for teams the user belongs to
myOpenPRsRequestobject
Request for user's open pull requests across all Git repositories
myEntitiesRequestobject
Request for all entities (services, resources, domains) owned by the user
myWorkItemsRequestobject
Request for work items (Jira, Linear, Azure DevOps issues) assigned to the user
myScorecardsRequestobject
Request for scorecards associated with the user's entities
myRequestedReviewsRequestobject
Request for pull requests where the user is requested as a reviewer
listRelationshipTypesList all available relationship types with pagination. View relationship type configurations to understand what kinds of relationships can be created between entities like services, resources, domains, and teams3 params

List all available relationship types with pagination. View relationship type configurations to understand what kinds of relationships can be created between entities like services, resources, domains, and teams

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
getRelationshipTypeDetailsGet complete details of a specific relationship type including its configuration, rules, source/destination filters, and inheritance settings. Essential for understanding how entities can be connected and what validation rules apply2 params

Get complete details of a specific relationship type including its configuration, rules, source/destination filters, and inheritance settings. Essential for understanding how entities can be connected and what validation rules apply

Parameters* required
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
relationshipTypeTagstring
listEntityRelationshipsList all entity relationships/full graph for a specific relationship type across the entire organization. Returns paginated results showing all source-destination pairs, useful for understanding the complete relationship graph and finding all connections of a particular type4 params

List all entity relationships/full graph for a specific relationship type across the entire organization. Returns paginated results showing all source-destination pairs, useful for understanding the complete relationship graph and finding all connections of a particular type

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
relationshipTypeTagstring
listScorecardsList all scorecards in the organization with optional filtering. View scorecard configurations to understand quality standards, compliance requirements, and maturity models. Supports filtering by groups, entities, and teams to find relevant scorecards7 params

List all scorecards in the organization with optional filtering. View scorecard configurations to understand quality standards, compliance requirements, and maturity models. Supports filtering by groups, entities, and teams to find relevant scorecards

Parameters* required
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
teamsarray
Filter based on team (either tags or CIDs). Accepts a comma-delimited list of team tag or CIDs, please use only one type of identifier
groupsarray
Filter based on groups, which correspond to the `x-cortex-groups` field in the Catalog Descriptor. Accepts a comma-delimited list of groups
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
entitiesarray
Filter based on entity (either tags or CIDs). Accepts a comma-delimited list of entity tag or CIDs, please use only one type of identifier
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
showDraftsboolean
getScorecardGet complete details of a scorecard including its configuration, rules, levels, weights, exemption settings, and evaluation criteria. Essential for understanding how services are evaluated and what standards they must meet2 params

Get complete details of a scorecard including its configuration, rules, levels, weights, exemption settings, and evaluation criteria. Essential for understanding how services are evaluated and what standards they must meet

Parameters* required
tagstring
Unique tag for the Scorecard
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
getScorecardNextStepsForEntityGet actionable next steps for an entity to improve its scorecard performance. Shows which rules need to be satisfied to reach the next maturity level, helping teams prioritize improvements and track progress toward compliance goals3 params

Get actionable next steps for an entity to improve its scorecard performance. Shows which rules need to be satisfied to reach the next maturity level, helping teams prioritize improvements and track progress toward compliance goals

Parameters* required
tagstring
Unique tag for the Scorecard
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
entityTagstring
The entity tag (`x-cortex-tag`) that identifies the entity.
listScorecardScoresRetrieve scores for all entities evaluated by a specific scorecard. Returns paginated results showing how each service, resource, or domain performs against the scorecard's rules, including individual rule scores and overall scorecard scores5 params

Retrieve scores for all entities evaluated by a specific scorecard. Returns paginated results showing how each service, resource, or domain performs against the scorecard's rules, including individual rule scores and overall scorecard scores

Parameters* required
tagstring
Unique tag for the Scorecard
pageinteger
Page number to return, 0-indexed. Default 0.default: 0
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
pageSizeinteger
Number of results to return per page, between 1 and 1000. Default 250.default: 250
entityTagstring
Entity tag (x-cortex-tag)
getTeamDetailsRetrieve detailed information about a specific team by its tag or ID. Returns complete team data including members, slack channels, metadata, and whether it's backed by an identity provider group2 params

Retrieve detailed information about a specific team by its tag or ID. Returns complete team data including members, slack channels, metadata, and whether it's backed by an identity provider group

Parameters* required
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
tagOrIdstring
Entity identifier - can be a tag or CID
query_docsQuery the Cortex knowledge base for answers. Args: query: The question to ask Cortex docs Returns: Response from Cortex including answer and metadata2 params

Query the Cortex knowledge base for answers. Args: query: The question to ask Cortex docs Returns: Response from Cortex including answer and metadata

Parameters* required
querystring
contextstring
Explain why you're invoking this tool now and how its output will be used. Then state how this call supports your *overall objective* and fits into your broader plan across all tool calls (e.g., why this tool vs. others, and what step it unblocks). Never share any personal details or sensitive information.
get_more_toolsCheck for additional tools whenever your task might benefit from specialized capabilities - even if existing tools could work as a fallback.1 params

Check for additional tools whenever your task might benefit from specialized capabilities - even if existing tools could work as a fallback.

Parameters* required
contextvalue
default:

Cortex

CI PyPI Python License

Cognitive knowledge system with formal ontology, reasoning, and intelligence serving.

Cortex captures knowledge objects (decisions, lessons, fixes, sessions, research, ideas), classifies them with an OWL-RL ontology, discovers relationships, reasons over the graph, and serves intelligence through hybrid retrieval.

Dashboard

Knowledge Graph

Install

pip install abbacus-cortex[embeddings]
cortex setup

The setup wizard configures everything: LLM provider, embeddings, dashboard password, background services, and Claude Code registration.

Other install methods

Lightweight (no PyTorch — wizard offers to install embeddings):

pip install abbacus-cortex
cortex setup

Homebrew:

brew install abbacusgroup/cortex/abbacus-cortex
cortex setup

From source:

git clone https://github.com/abbacusgroup/Cortex.git && cd Cortex
uv sync --extra embeddings
cortex setup

Docker:

docker compose up -d

For non-interactive installs (CI, scripts): cortex setup --auto uses environment variables.

Quick Start

cortex capture "Fix: Neo4j pool exhaustion" --type fix --content "Root cause was..."
cortex search "Neo4j"
cortex list
cortex context "Neo4j"
cortex dashboard                    # web UI at http://localhost:1315

Configuration

cortex setup writes configuration to ~/.cortex/.env. You can also edit it directly:

CORTEX_LLM_PROVIDER=anthropic
CORTEX_LLM_MODEL=claude-sonnet-4-20250514
CORTEX_LLM_API_KEY=sk-...
CORTEX_EMBEDDING_MODEL=all-mpnet-base-v2

Cortex loads .env from these locations in priority order: environment variables (highest), .env in the current working directory, then ~/.cortex/.env. The recommended location is ~/.cortex/.env for persistent configuration.

See .env.example for all options.

CLI Commands

CommandDescription
cortex setupInteractive setup wizard
cortex initInitialize data directory and stores (deprecated — use cortex setup)
cortex installInstall background services (macOS/Linux)
cortex uninstallRemove background services
cortex registerRegister MCP server with Claude Code
cortex captureCapture a knowledge object
cortex searchHybrid keyword + semantic search
cortex readRead object in full
cortex listList objects with filters
cortex statusHealth and counts
cortex contextBriefing mode (summaries)
cortex dossierEntity-centric intelligence brief
cortex graphShow object relationships
cortex synthesizeCross-document synthesis
cortex entitiesList resolved entities
cortex serveStart MCP or HTTP server
cortex dashboardStart web dashboard
cortex backupBackup data directory to archive
cortex restoreRestore from backup archive
cortex doctorDiagnostics: check, unlock, logs, repair
cortex pipelineRe-run intelligence pipeline on an object
cortex reasonRun advanced reasoning (contradictions, patterns, gaps)
cortex import-v1Import from Cortex v1 database
cortex import-vaultImport from Obsidian vault

MCP Tools

26 tools for AI agent integration. Localhost-bound HTTP exposes all; non-localhost binds expose only the public set.

Public: cortex_search, cortex_context, cortex_dossier, cortex_read, cortex_capture, cortex_link, cortex_feedback, cortex_graph, cortex_list, cortex_classify, cortex_pipeline

Admin (localhost only): cortex_status, cortex_synthesize, cortex_delete, cortex_delete_entity, cortex_update, cortex_unlink, cortex_reason, cortex_query_trail, cortex_graph_data, cortex_list_entities, cortex_export, cortex_import, cortex_safety_check, cortex_debug_sessions, cortex_debug_memory

Architecture

Cortex runs as a single MCP HTTP server that owns the graph store. Claude Code, the dashboard, the CLI, and the REST API are all HTTP clients of that one server.

┌───────────────┐    ┌────────────┐    ┌─────────────┐
│ Claude Code   │    │  Dashboard │    │     CLI     │
│ (MCP client)  │    │ (browser)  │    │  (terminal) │
└───────┬───────┘    └─────┬──────┘    └──────┬──────┘
        │                  │                  │
        │ HTTP JSON-RPC    │ HTTP MCP         │ HTTP MCP (default)
        │                  │                  │ direct (--direct)
        ▼                  ▼                  ▼
        ┌──────────────────────────────────────┐
        │   cortex serve --transport mcp-http  │
        │   (canonical MCP HTTP server)        │
        │   PID-locked owner of graph.db       │
        └──────────────────────────────────────┘
                          │
                          ▼
            ┌─────────────────────────────┐
            │  ~/.cortex/                 │
            │    graph.db   (Oxigraph)    │
            │    cortex.db  (SQLite WAL)  │
            └─────────────────────────────┘
  • Ontology: OWL-RL formal ontology with 8 knowledge types and 8 relationship types
  • Storage: Oxigraph (RDF/SPARQL) + SQLite (FTS5/BM25) dual-write
  • Pipeline: Classify → Extract entities → Link → Enrich → Reason
  • Retrieval: Hybrid keyword + semantic + graph-boosted ranking
  • Serving: 5 presentation modes (briefing, dossier, document, synthesis, alert)
  • Transports: MCP (stdio + HTTP), REST API, Web Dashboard

Service Management

# Install both MCP server and dashboard as background services
cortex install

# Install only the MCP server
cortex install --service mcp

# Remove all services
cortex uninstall

On macOS, this creates LaunchAgent plists (auto-start on login, auto-restart on crash). On Linux, this creates systemd user units.

Raw templates are available in deploy/ for manual setup.

--direct escape hatch

By default, CLI commands route through the running MCP server. If the server is down:

cortex --direct list               # bypass MCP, open store directly
cortex --direct pipeline --batch   # required for bulk SQL operations

Bootstrap commands (init, setup, import-v1, import-vault) always run directly.

Docker

docker compose up -d
# Server at http://localhost:1314

Troubleshooting

Crashed MCP server

If the MCP server is killed hard, stale lock files auto-recover on next start. For manual cleanup:

cortex doctor unlock              # normal cleanup
cortex doctor unlock --dry-run    # report only
cortex doctor unlock --force      # bypass live-holder check

Log management

cortex doctor logs                # show log file sizes and status
cortex doctor logs --tail 20      # last 20 lines
cortex doctor logs --rotate       # rotate log files (safe while running)

Claude Code session staleness

After restarting the MCP server, restart Claude Code to clear its stale session ID. claude --resume restores your conversation. The dashboard and CLI do not have this issue.

Knowledge Types

decision, lesson, fix, session, research, source, synthesis, idea

Relationship Types

causedBy, contradicts (symmetric), supports, supersedes (transitive), dependsOn, ledTo (inverse of causedBy), implements, mentions

Privacy

Cortex stores all data locally. No telemetry, no analytics, no phone-home. If you configure an LLM provider (via CORTEX_LLM_API_KEY), object content may be sent to that provider for classification and reasoning. Embeddings are computed locally by default using sentence-transformers.

License

Copyright (c) 2026 Abbacus Group. Licensed under the MIT License.

Trademark Notice

Cortex is a project of Abbacus Group and is not affiliated with any other product named Cortex.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
Documents & Knowledge
Registryactive
Packageabbacus-cortex
TransportSTDIO
UpdatedApr 12, 2026
View on GitHub

Related Documents & Knowledge MCP Servers

View all →
Pdf Document Mcp

csoai-org/pdf-document-mcp

pdf-document-mcp MCP server by MEOK AI Labs
Mcp Document Converter

xt765/mcp-document-converter

Convert PDF, DOCX, HTML, Markdown, and Text for AI assistant context injection.
10
Markdown Formatter

io.github.xjtlumedia/markdown-formatter

AI Answer Copier — Convert Markdown to PDF, DOCX, HTML, LaTeX, CSV, JSON, XML, XLSX, RTF, PNG
3
Better Notion

io.github.ai-aviate/better-notion

Operate Notion with a single Markdown document — read, create, and update pages in one call.
2
Notion

suekou/mcp-notion-server

Notion MCP Server enables LLMs to access Notion workspaces with optional Markdown conversion to save tokens.
892
Docx

meterlong/mcp-doc

A powerful Word document processing service based on FastMCP, enabling AI assistants to create, edit, and manage docx files with full formatting support. Preserves original styles when editing content. 基于FastMCP的强大Word文档处理服务,使AI助手能够创建、编辑和管理docx文件,支持完整的格式设置功能。在编辑内容时能够保留原始样式和格式,实现精确的文档操作。
185