Summary
Persistent memory and knowledge graphs for AI agents that survive across sessions. Exposes 17 tools including store, recall, search for memory operations, connect and explore for building knowledge graphs, and awaken/reflect for loading context at session start. Uses hybrid search combining BM25, vector, and graph traversal. Syncs across Claude, Cursor, Windsurf, Gemini CLI, and other MCP clients through a remote server at mcp.penfield.app. Reach for this when you need your agent to remember decisions, preferences, and investigation threads between conversations, or when building compound knowledge over time instead of starting cold every session.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
17 tools
awaken⚡ CALL THIS TOOL FIRST IN EVERY NEW CONVERSATION ⚡ Loads your personality configuration and user preferences for this session. This is how you learn WHO you are and HOW the user wants you to behave. Returns your awakening briefing containing: - Your persona identity (who you a...
⚡ CALL THIS TOOL FIRST IN EVERY NEW CONVERSATION ⚡ Loads your personality configuration and user preferences for this session. This is how you learn WHO you are and HOW the user wants you to behave. Returns your awakening briefing containing: - Your persona identity (who you a...
No parameter schema in public metadata yet.
searchSearch for memories. Returns results with proper citation support (id, title, url, text fields). Args: query: Search query limit: Maximum results (default 10) ctx: MCP context Returns: Dict with 'results' array containing id, title, url, text fields2 params
Search for memories. Returns results with proper citation support (id, title, url, text fields). Args: query: Search query limit: Maximum results (default 10) ctx: MCP context Returns: Dict with 'results' array containing id, title, url, text fields
Parameters* required
limitintegerdefault: 10
querystringfetchFetch memory by ID. Returns a single memory with proper citation support (id, title, url, text fields). Args: id: Memory UUID to fetch ctx: MCP context Returns: Dict with id, title, url, text, metadata fields1 params
Fetch memory by ID. Returns a single memory with proper citation support (id, title, url, text fields). Args: id: Memory UUID to fetch ctx: MCP context Returns: Dict with id, title, url, text, metadata fields
Parameters* required
idstringstoreStore important information from your work. Write detailed, complete thoughts with context, reasoning, and evidence. **Always use the connect tool** to link related items - this builds knowledge graphs for better recall. ## Memory Types (auto-detected, but be aware): - **FACT*...3 params
Store important information from your work. Write detailed, complete thoughts with context, reasoning, and evidence. **Always use the connect tool** to link related items - this builds knowledge graphs for better recall. ## Memory Types (auto-detected, but be aware): - **FACT*...
Parameters* required
tagsvaluecontentstringimportancevalueupdate_memoryUpdate an existing memory. Modifies properties of a stored memory by its UUID. Args: memory_id: UUID of memory to update content: New content (optional) importance: New importance score (optional, 0.0-1.0) tags: New tags (optional, replaces existing tags) ctx: MCP context (aut...4 params
Update an existing memory. Modifies properties of a stored memory by its UUID. Args: memory_id: UUID of memory to update content: New content (optional) importance: New importance score (optional, 0.0-1.0) tags: New tags (optional, replaces existing tags) ctx: MCP context (aut...
Parameters* required
tagsvaluecontentvaluememory_idstringimportancevalueconnectConnect memories to build knowledge graphs. After using 'store', immediately connect related memories using these relationship types: ## Knowledge Evolution - **supersedes**: This replaces → outdated understanding - **updates**: This modifies → existing knowledge - **evolution...4 params
Connect memories to build knowledge graphs. After using 'store', immediately connect related memories using these relationship types: ## Knowledge Evolution - **supersedes**: This replaces → outdated understanding - **updates**: This modifies → existing knowledge - **evolution...
Parameters* required
strengthvalueto_memorystringfrom_memorystringrelationship_typestringdisconnectRemove a connection between memories. Deletes the relationship between two memories in the knowledge graph. Args: from_memory: Source memory UUID to_memory: Target memory UUID ctx: MCP context (automatically provided) Returns: Dict with success status and disconnected memory I...2 params
Remove a connection between memories. Deletes the relationship between two memories in the knowledge graph. Args: from_memory: Source memory UUID to_memory: Target memory UUID ctx: MCP context (automatically provided) Returns: Dict with success status and disconnected memory I...
Parameters* required
to_memorystringfrom_memorystringsave_contextSave your cognitive state for handoff to another agent. Include your investigation context: - What session/investigation is this part of? - What role/perspective were you taking? - Who might pick this up next? (another Claude, human, Claude Code?) Reference specific memories t...2 params
Save your cognitive state for handoff to another agent. Include your investigation context: - What session/investigation is this part of? - What role/perspective were you taking? - Who might pick this up next? (another Claude, human, Claude Code?) Reference specific memories t...
Parameters* required
namestringdescriptionvaluerecallRecall relevant information. Uses hybrid search to find relevant memories, documents, and connections. Args: query: What to search for source_type: Optional filter ('memory', 'document', or None for all) tags: Optional list of tags to filter by (OR logic - memories with ANY of...6 params
Recall relevant information. Uses hybrid search to find relevant memories, documents, and connections. Args: query: What to search for source_type: Optional filter ('memory', 'document', or None for all) tags: Optional list of tags to filter by (OR logic - memories with ANY of...
Parameters* required
tagsvaluelimitintegerdefault: 10
querystringend_datevaluestart_datevaluesource_typevalueexploreExplore connections from a memory. Traverses the knowledge graph to find related concepts, following relationships up to the specified depth. Args: start_memory: Starting memory UUID max_depth: How deep to traverse (default 3, max 10) relationship_types: Filter by specific rel...3 params
Explore connections from a memory. Traverses the knowledge graph to find related concepts, following relationships up to the specified depth. Args: start_memory: Starting memory UUID max_depth: How deep to traverse (default 3, max 10) relationship_types: Filter by specific rel...
Parameters* required
max_depthintegerdefault: 3
start_memorystringrelationship_typesvaluerestore_contextResume work from a saved cognitive context. This provides a narrative briefing to quickly orient you to: - The investigation that was in progress - Key discoveries and insights made - Current hypotheses being tested - Open questions and blockers - Suggested next steps - All re...2 params
Resume work from a saved cognitive context. This provides a narrative briefing to quickly orient you to: - The investigation that was in progress - Key discoveries and insights made - Current hypotheses being tested - Open questions and blockers - Suggested next steps - All re...
Parameters* required
namestringlimitintegerdefault: 20
list_contextsList available context checkpoints. Shows all saved contexts available for multi-agent workflows. Args: limit: Maximum number of contexts to return (default 20, max 100) offset: Number of contexts to skip for pagination (default 0) name_pattern: Filter contexts by name (case-i...4 params
List available context checkpoints. Shows all saved contexts available for multi-agent workflows. Args: limit: Maximum number of contexts to return (default 20, max 100) offset: Number of contexts to skip for pagination (default 0) name_pattern: Filter contexts by name (case-i...
Parameters* required
limitintegerdefault: 20
offsetintegerdefault: 0
name_patternvalueinclude_descriptionsbooleandefault: false
reflectReflect on recent thoughts and patterns. Analyzes recent activity to identify patterns, topics, and insights. Useful for understanding "what have I been thinking about?" By default, only returns user-created memories (not document chunks). Set include_documents=True to also in...4 params
Reflect on recent thoughts and patterns. Analyzes recent activity to identify patterns, topics, and insights. Useful for understanding "what have I been thinking about?" By default, only returns user-created memories (not document chunks). Set include_documents=True to also in...
Parameters* required
end_datevaluestart_datevaluetime_windowvaluedefault: recent
include_documentsbooleandefault: false
save_artifactSave an artifact to storage. Stores user-created content (diagrams, notes, code) in an organized file structure. Content is also indexed for search. Args: content: File content to save path: Full path including filename (e.g., "/project/docs/api.md") Returns: Success message o...2 params
Save an artifact to storage. Stores user-created content (diagrams, notes, code) in an organized file structure. Content is also indexed for search. Args: content: File content to save path: Full path including filename (e.g., "/project/docs/api.md") Returns: Success message o...
Parameters* required
pathstringcontentstringretrieve_artifactRetrieve an artifact from storage. Fetches the content of a previously saved artifact. Args: path: Full path of the artifact (e.g., "/project/docs/api.md") Returns: Artifact content or error message Examples: >>> await retrieve_artifact("/readme.md") "# README\nThis is the rea...1 params
Retrieve an artifact from storage. Fetches the content of a previously saved artifact. Args: path: Full path of the artifact (e.g., "/project/docs/api.md") Returns: Artifact content or error message Examples: >>> await retrieve_artifact("/readme.md") "# README\nThis is the rea...
Parameters* required
pathstringlist_artifactsList artifacts in a directory. Returns the immediate contents of a directory (not recursive). Separates folders and files for easy navigation. Args: path_prefix: Directory path to list (default: "/") Returns: Formatted directory listing or error message Examples: >>> await lis...1 params
List artifacts in a directory. Returns the immediate contents of a directory (not recursive). Separates folders and files for easy navigation. Args: path_prefix: Directory path to list (default: "/") Returns: Formatted directory listing or error message Examples: >>> await lis...
Parameters* required
path_prefixstringdefault: /
delete_artifactDelete an artifact from storage. Permanently removes an artifact and its associated memory record. Args: path: Full path of the artifact to delete ctx: MCP context (automatically provided) Returns: Dict with success status1 params
Delete an artifact from storage. Permanently removes an artifact and its associated memory record. Args: path: Full path of the artifact to delete ctx: MCP context (automatically provided) Returns: Dict with success status
Parameters* required
pathstringPenfield
Persistent memory for AI agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Works with Claude, Cursor, Windsurf, Gemini CLI, and any MCP-compatible tool.
Quick Start
Claude (Desktop, Mobile, Web)
Add as a custom connector in Settings → Connectors:
Name: Penfield
Remote MCP server URL: https://mcp.penfield.app
Claude Code
claude mcp add --transport http --scope user penfield https://mcp.penfield.app
Cursor
One-click install:
Cut and paste into your browser:
cursor://anysphere.cursor-deeplink/mcp/install?name=Penfield&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIm1jcC1yZW1vdGUiLCJodHRwczovL21jcC5wZW5maWVsZC5hcHAvIl19
Or add manually to ~/.cursor/mcp.json:
{
"mcpServers": {
"Penfield": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.penfield.app/"]
}
}
}
Windsurf, Cline, Roo Code, and Others
Add to your MCP configuration file:
{
"mcpServers": {
"Penfield": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.penfield.app/"]
}
}
}
| App | Config Location |
|---|---|
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| Cline | VS Code Settings → Cline → MCP Servers |
| Roo Code | VS Code Settings → Roo Code → MCP Servers |
| Zed | ~/.config/zed/settings.json under "context_servers" |
Gemini CLI
gemini mcp add penfield -- npx -y mcp-remote https://mcp.penfield.app/
Or add to ~/.gemini/settings.json:
{
"mcpServers": {
"Penfield": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.penfield.app/"]
}
}
}
What You Get
17 tools for persistent memory:
| Category | Tools |
|---|---|
| Memory | store, recall, search, fetch, update_memory |
| Knowledge Graph | connect, disconnect, explore |
| Context | awaken, reflect, save_context, restore_context, list_contexts |
| Artifacts | save_artifact, retrieve_artifact, list_artifacts, delete_artifact |
Hybrid search combining BM25 (keyword), vector (semantic), and graph (connections) for recall that actually finds what you need.
Cross-platform sync — same memory, same knowledge graph, regardless of which tool you connect from.
How It Works
- Sign up at portal.penfield.app/sign-up
- Connect using one of the methods above
- Authenticate when prompted (OAuth flow)
- Start using — your agent now has persistent memory
Every session should start with:
awaken() # Load identity and personality context
reflect() # Orient on recent work (default: last 7 days)
Without these, your agent starts cold with no context.
Documentation
- Tools Reference — All 17 tools with parameters and examples
- Memory Types — The 11 memory types and when to use each
- Relationships — The 24 relationship types for connecting memories
- AI Agent Guide — Instructions for AI agents using Penfield
Use Cases
Personal assistant that remembers
- Your preferences compound over time
- Picks up conversations where you left off
- Learns how you like things done
Development workflows
- Track investigation threads across sessions
- Remember architectural decisions and why they were made
- Hand off context between coding sessions
Research and writing
- Build knowledge graphs of connected ideas
- Store insights and corrections as understanding evolves
- Checkpoint progress on long-running projects
Also Available
OpenClaw Native Plugin — If you use OpenClaw, the native plugin is 4-5x faster (no MCP proxy layer):
openclaw plugins install openclaw-penfield
openclaw penfield login
openclaw-penfield on GitHub · openclaw-penfield on npm
API — Direct HTTP access at api.penfield.app for custom integrations.
Links
- MCP: mcp.penfield.app
- Website: penfield.app
- Portal: portal.penfield.app
- Cursor Directory: cursor.directory/mcp/penfield
- X: @penfieldlabs
- GitHub: @penfieldlabs
Copyright © 2025 Penfield™. All rights reserved.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Registryactive
TransportHTTP
UpdatedFeb 2, 2026
