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

Axiom Agentic Tools

0xaxiom/axiom-agentic-tools
16 toolsHTTPregistry active
Summary

Five deterministic tools for shipping agent infrastructure on Base, paid via x402 USDC transfers with no API keys or accounts. You get a revenue optimizer that audits any x402 endpoint for leaks, a token spec generator with OZ templates and deploy costs, a workflow planner that chains paid tools under budget, a Base grant finder, and a free tier repo health check that scores marketplace readiness across 15 criteria. Works over MCP streamable HTTP in Claude Code, Cursor, Cline, and Windsurf, or raw HTTP with EIP-3009 payment headers. Payments settle through the Coinbase CDP facilitator, so you show up in agentic.market and the Bazaar indexer automatically.

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.

6 tools
agent-revenue-optimizerAudit an x402-gated endpoint by probing its 402 envelope, agent-card.json, well-known surfaces, and response headers. Returns a closed-vocabulary verdict plus 3-7 scored recommendations across pricing, bundling, discoverability, envelope correctness, rate limiting, tier expans...2 params

Audit an x402-gated endpoint by probing its 402 envelope, agent-card.json, well-known surfaces, and response headers. Returns a closed-vocabulary verdict plus 3-7 scored recommendations across pricing, bundling, discoverability, envelope correctness, rate limiting, tier expans...

Parameters* required
endpoint_urlstring
Public HTTP(S) URL of the x402-gated endpoint to audit. Must respond with an HTTP 402 envelope on an unauthenticated GET (or POST). Example: https://x402.org or any /api/tools/<slug> on a deployed x402 service.
assumed_monthly_paid_callsinteger
Optional estimate of how many paid calls per month the endpoint currently receives. Used to scale recommendation impact_usd_per_month from a per-call delta to a monthly figure. Defaults to 1000 if omitted.
agent-token-strategyDesign a non-security token strategy for an autonomous agent. Returns a deployable spec: symbol, supply, distribution allocations summing to 100, OpenZeppelin contract templates (ERC20, ERC4626, ERC721), fair-launch defaults, a six-criterion non-security checklist, an estimate...5 params

Design a non-security token strategy for an autonomous agent. Returns a deployable spec: symbol, supply, distribution allocations summing to 100, OpenZeppelin contract templates (ERC20, ERC4626, ERC721), fair-launch defaults, a six-criterion non-security checklist, an estimate...

Parameters* required
symbolstring
Ticker symbol, 2-10 chars, A-Z and digits, leading letter.
patternstring
Which template to base the strategy on.one of fair-launch-axiom-style · staking-loop · minimal-erc20
agent_namestring
Display name of the agent the token represents.
include_nftboolean
Include an ERC721 access pass alongside the ERC20.
total_supplyinteger
Optional total supply override. Defaults to template default.
base-builder-grant-finderReturns a ranked, deadline-aware list of open Base ecosystem funding programs (grants, accelerators, hackathons, retro-funding). Each result cites source_url, deadline, funding_range_usd, and last_verified_at. Stale entries are flagged. Designed for agents and builders shippin...4 params

Returns a ranked, deadline-aware list of open Base ecosystem funding programs (grants, accelerators, hackathons, retro-funding). Each result cites source_url, deadline, funding_range_usd, and last_verified_at. Stale entries are flagged. Designed for agents and builders shippin...

Parameters* required
stagestring
Current project stage. 'idea' is pre-prototype; 'prototype' has working demo; 'mainnet' has deployed Base contracts; 'scaling' has live users and revenue. Used as an additional eligibility filter against grant stage requirements. Defaults to 'any'.one of idea · prototype · mainnet · scaling · anydefault: any
categorystring
Project category. Used to match grant program eligibility and scope. 'ai-agent' covers agent infrastructure, autonomous agents, and agent-economy projects; 'tooling' covers dev tools and SDKs; 'any' returns programs that accept all categories. Required.one of defi · infra · ai-agent · consumer · nft · tooling
max_resultsinteger
Maximum number of ranked program results to return. Programs are scored by match against category, stage, has_live_base_contract, and deadline proximity. Defaults to 10.default: 10
has_live_base_contractboolean
True if the project already has at least one deployed contract on Base mainnet. Several grants (Base Builder Grants, Coinbase Developer Grants) score higher for live-on-Base projects. Defaults to false.default: false
mcp-security-scannerScans an MCP server manifest or endpoint for security vulnerabilities — prompt injection in tool descriptions, exfiltration vectors, unbounded resource access, privilege escalation, schema mismatches, transport security issues, and over-permissive scopes. Returns a structured...3 params

Scans an MCP server manifest or endpoint for security vulnerabilities — prompt injection in tool descriptions, exfiltration vectors, unbounded resource access, privilege escalation, schema mismatches, transport security issues, and over-permissive scopes. Returns a structured...

Parameters* required
checksarray
Specific check categories to run. Omit to run all checks.
manifestUrlstring
URL of the MCP server manifest (e.g. https://example.com/.well-known/agentic/manifest.json). Mutually exclusive with manifestJson.
manifestJsonobject
Raw MCP manifest JSON object to scan. Mutually exclusive with manifestUrl.
multi-agent-workflow-designerCompose a directed acyclic graph of public x402, MCP, and A2A tools that achieves a stated agent goal. Returns step-by-step plan with tool slug, endpoint URL, protocol, inputs, dependencies, per-step cost and latency, total estimated cost, and an executable plan in either a2a-...5 params

Compose a directed acyclic graph of public x402, MCP, and A2A tools that achieves a stated agent goal. Returns step-by-step plan with tool slug, endpoint URL, protocol, inputs, dependencies, per-step cost and latency, total estimated cost, and an executable plan in either a2a-...

Parameters* required
goalstring
Plain-English agent goal, e.g. 'sweep top 5 floor NFTs in collection X if contract is safe and gas is low'.
max_stepsinteger
Cap on number of steps in the returned DAG.
budget_usdnumber
Maximum total spend across all chained tool calls. Steps over budget are pruned.
output_formatstring
Executable plan format. Defaults to a2a-json-rpc.one of a2a-json-rpc · shell-curl
preferred_protocolsarray
Restrict catalog selection to these protocols. Empty = all.
repo-health-for-agentsFree agent-marketplace-readiness audit. Runs a 15-check scorecard (agent-card, MCP descriptor, OpenAPI, llms.txt, x402 envelope, CDP facilitator, Bazaar discoverability, ERC-8257 registration, ERC-8004 identity, CI demo, schema drift, README marketplace mentions, license) on a...3 params

Free agent-marketplace-readiness audit. Runs a 15-check scorecard (agent-card, MCP descriptor, OpenAPI, llms.txt, x402 envelope, CDP facilitator, Bazaar discoverability, ERC-8257 registration, ERC-8004 identity, CI demo, schema drift, README marketplace mentions, license) on a...

Parameters* required
repostring
GitHub owner/name (e.g. 0xAxiom/axiom-agentic-tools)
branchstring
Optional branch (defaults to default branch on GitHub)
deployed_urlstring
Optional deployed base URL to probe (e.g. https://agentic.clawbots.org)

Axiom Agentic Tools

Five JSON-output MCP tools for builders shipping agentic services on Base. x402-paid, no API keys, no accounts.

MCP Registry Smithery x402 Base License: MIT MCP

Live deployment: agentic.clawbots.org · MCP endpoint: /api/agentic/mcp · OpenAPI: /api/agentic/openapi.json


Overview

axiom-agentic-tools is a tiny, deterministic MCP server. Each of its five tools answers one focused question for an autonomous agent or its builder:

  • "Where is this x402 endpoint leaking revenue?"
  • "What does a deployable token spec look like for my agent?"
  • "Which sequence of paid tools fits this budget?"
  • "Is my repo ready for agent marketplaces?"
  • "Which Base grant should I apply to next?"

The server is callable three ways:

  • MCP — streamable-HTTP, current protocol 2025-11-25. Works in Claude Code, Cursor, Cline, Windsurf, OpenAI Agent Builder, Smithery Toolbox.
  • HTTP + x402 — POST /api/agentic/tools/<slug> with an EIP-3009 transferWithAuthorization in the X-PAYMENT header.
  • A2A — discoverable via /.well-known/agent-card.json on the parent.

Payments settle in USDC on Base through the Coinbase CDP facilitator (the indexer source for agentic.market and the Coinbase Bazaar).

Features

  • ✅ x402 v2 envelope — top-level resource, extensions.bazaar, PAYMENT-REQUIRED response header per specs/transports-v2/http.md.
  • ✅ MCP 2025-11-25 — initialize, tools/list, tools/call. Tool call dispatches in-process; payment runs once, not twice.
  • ✅ Bazaar-ready — extensions.bazaar.info.input.type: "http", output schema + example, route template, JSON Schema all in the 402.
  • ✅ GET discovery — unauthenticated GET returns a 402 with the envelope, so validators can introspect without a body.
  • ✅ Deterministic — closed-vocabulary JSON outputs, schema-validated on every response. No "the model said…" drift.
  • ✅ Free tier — repo-health-for-agents runs at 50/day per IP with no payment.
  • ✅ Rate-limited — 60/hr per IP on paid tools, 10/hr on ?preview=1.

Tools

SlugPriceReturns
agent-revenue-optimizer$0.10Probes any x402 endpoint → closed-vocab verdict + 3–7 scored recommendations across pricing, bundling, discoverability, envelope, rate-limit, facilitator.
agent-token-strategy$0.15Token spec for an autonomous agent: symbol, allocations, OZ template, fair-launch checklist, deploy cost estimate, risk list.
multi-agent-workflow-designer$0.10DAG of public x402/MCP/REST tools that hits a goal under a USD budget, with per-step cost + latency + runnable curl.
base-builder-grant-finder$0.05Ranked, deadline-aware list of open Base ecosystem grants / accelerators / hackathons / retro-funding.
repo-health-for-agentsfree*15-check 0–100 marketplace-readiness audit of a public GitHub repo. Each check carries pass/fail + URL evidence.

free at 50 calls/day/IP, then 402.

Quick start

From an MCP-aware editor

Add this server to your MCP client config and axiom-* tools appear in your tool palette immediately. No install, no auth.

Claude Code

claude mcp add --transport http axiom https://agentic.clawbots.org/api/agentic/mcp

Cursor

Cursor → Settings → MCP → New MCP server:

{
  "name": "axiom",
  "type": "http",
  "url": "https://agentic.clawbots.org/api/agentic/mcp"
}

Cline

Cline → Settings → MCP servers → Configure MCP servers:

{
  "mcpServers": {
    "axiom": {
      "type": "streamableHttp",
      "url": "https://agentic.clawbots.org/api/agentic/mcp"
    }
  }
}

Windsurf

Windsurf → Settings → MCP → Add server:

{
  "mcpServers": {
    "axiom": {
      "serverUrl": "https://agentic.clawbots.org/api/agentic/mcp"
    }
  }
}

Smithery Toolbox

Install from Smithery with one click.

From AgentKit

Use all 6 tools as native AgentKit actions. The wallet provider handles x402 payment automatically.

import { AgentKit } from "@coinbase/agentkit";
import { axiomToolsProvider } from "@axiom-tools/agentkit-provider";

const agentkit = await AgentKit.from({
  walletProvider,
  actionProviders: [axiomToolsProvider()],
});

See agentkit/ for the full action provider and docs.

From raw HTTP

# 1. Discovery — what does this endpoint cost?
curl -sX GET https://agentic.clawbots.org/api/agentic/tools/agent-revenue-optimizer \
  -D /tmp/h | head -10
#   HTTP/2 402
#   PAYMENT-REQUIRED: <base64 envelope>

# 2. Decode the envelope:
grep -i payment-required: /tmp/h | cut -d' ' -f2- | tr -d '\r' | base64 -d | jq .

# 3. Sign + retry (@x402/fetch v2 handles this for you):
# npm i @x402/fetch @x402/evm viem
node -e "
import('@x402/fetch').then(async ({ wrapFetchWithPayment, x402Client }) => {
  const { privateKeyToAccount } = await import('viem/accounts');
  const { ExactEvmScheme } = await import('@x402/evm/exact/client');
  const account = privateKeyToAccount(process.env.X402_PRIVATE_KEY);
  const client = new x402Client().register('eip155:8453', new ExactEvmScheme(account));
  const fetch = wrapFetchWithPayment(globalThis.fetch, client);
  const r = await fetch('https://agentic.clawbots.org/api/agentic/tools/agent-revenue-optimizer', {
    method: 'POST',
    headers: { 'content-type': 'application/json' },
    body: JSON.stringify({ endpoint_url: 'https://example.com/api/probe' }),
  });
  console.log(await r.json());
});
"

Installation (self-host)

You can host your own deployment — the only deploy target supported today is Vercel.

git clone https://github.com/0xAxiom/axiom-agentic-tools.git
cd axiom-agentic-tools
npm install
cp .env.example .env.local       # fill X402_PAY_TO + CDP_API_KEY_* (see Configuration)
npm run dev                      # vercel dev on :3000

Deploy:

vercel link                       # one-time
vercel --prod

Production smoke:

BASE=https://your-deployment.example npm test

Configuration

All configuration is via environment variables. Copy .env.example and fill in the blanks.

VariableRequiredDefaultPurpose
X402_PAY_TO✅—Your wallet address for paid tool revenue (USDC on Base).
X402_FACILITATOR_URL—https://api.cdp.coinbase.com/platform/v2/x402Facilitator endpoint. CDP is what Bazaar indexes.
CDP_API_KEY_ID✅ (if CDP)—CDP server-side credentials. Get them at portal.cdp.coinbase.com.
CDP_API_KEY_SECRET✅ (if CDP)——
X402_NETWORK—basebase or base-sepolia.
BASE_RPC_URL—https://mainnet.base.orgBase mainnet RPC. Use a private RPC in production.
PUBLIC_BASE_URL—(Vercel default)Absolute base URL of your deployment. Populates manifest/OpenAPI/discovery links.
GITHUB_TOKEN——Lifts the rate limit on tools that read public GitHub repos.

Usage examples

MCP tools/list

curl -s -X POST https://agentic.clawbots.org/api/agentic/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | jq '.result.tools[].name'

MCP tools/call

curl -s -X POST https://agentic.clawbots.org/api/agentic/mcp \
  -H 'content-type: application/json' \
  -H "x-payment: $X_PAYMENT_BASE64" \
  -d '{
    "jsonrpc":"2.0","id":2,"method":"tools/call",
    "params":{"name":"agent-revenue-optimizer","arguments":{"endpoint_url":"https://example.com/api/probe"}}
  }'

Free tier — repo-health-for-agents

curl -s -X POST https://agentic.clawbots.org/api/agentic/tools/repo-health-for-agents \
  -H 'content-type: application/json' \
  -d '{"repo":"your-org/your-repo"}'

50/day/IP free; over the limit returns the standard 402.

Architecture

Client (Claude / Cursor / curl)
        │
        ▼ POST /api/agentic/tools/<slug>
┌─────────────────────────────────────────────────┐
│  createAgenticRoute(spec, handler)              │
│   ├─ CORS + OPTIONS                             │
│   ├─ Rate limit (per-IP, 3 buckets)             │
│   ├─ Input validation (spec.inputSchema)        │
│   ├─ checkAccess(req)  ──► gate.mjs ──► x402   │
│   │      verify+settle through CDP facilitator  │
│   ├─ tool handler({ input, payment })           │
│   └─ Output validation (spec.outputSchema)      │
└─────────────────────────────────────────────────┘
        │
        ▼ JSON result + X-PAYMENT-RESPONSE header
  • api/agentic/mcp.mjs is an MCP transport. tools/call dispatches the same registry → x402 → handler pipeline in-process — payment runs once, never twice.
  • api/_lib/x402.mjs builds the v2 envelope (buildPaymentRequired) and shells out to the facilitator for verify/settle.
  • tools/<slug>/spec.mjs is the single source of truth for each tool: input/output schemas, price, examples, marketplace metadata, the bazaar extension block. Validated at boot and at prebuild.
  • scripts/generate-manifest.mjs regenerates /api/agentic/manifest, /api/agentic/openapi.json, /.well-known/agentic/tools/*.json, and the /.well-known/mcp.json server card from the registry.

Full reference: docs/ARCHITECTURE.md, docs/DESCRIPTOR.md, docs/DISCOVERY.md.

Development

npm install
npm run prebuild   # regenerate manifest + OpenAPI + .well-known
npm run dev        # vercel dev on :3000
npm test           # smoke (BASE=http://localhost:3000 by default)
npm run validate   # surface-consistency check

To add a tool, follow CONTRIBUTING.md §"Adding a new tool".

Verifying x402 v2 compliance

curl -sD- -X GET https://agentic.clawbots.org/api/agentic/tools/agent-revenue-optimizer \
  | head -20
# Expect:
#   HTTP/2 402
#   PAYMENT-REQUIRED: <base64>
# Body:
#   { "x402Version": 2, "resource": {…}, "accepts": [{ "amount": "100000", … }], "extensions": { "bazaar": {…} } }

The full compliance matrix lives in docs/X402_V2_COMPLIANCE_REPORT.md.

Discovery surfaces

SurfaceURL
MCP endpointhttps://agentic.clawbots.org/api/agentic/mcp
Tool manifesthttps://agentic.clawbots.org/api/agentic/manifest
OpenAPI 3.1https://agentic.clawbots.org/api/agentic/openapi.json
Health probehttps://agentic.clawbots.org/api/agentic/health
.well-known/agentic/tools/<slug>.jsonPer-tool descriptor (cached)
Bazaar extension schemahttps://agentic.clawbots.org/.well-known/schemas/x402-extension-bazaar-v2.json

Security

See SECURITY.md for the disclosure process. Report vulnerabilities privately via GitHub Private Vulnerability Reporting or email — do not open public issues for security findings.

Contributing

Pull requests welcome. Read CONTRIBUTING.md first — it's short, and it'll save you a round trip on style and surface conventions.

License

MIT.

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
AI & LLM Tools
Registryactive
TransportHTTP
UpdatedMay 31, 2026
View on GitHub

Related AI & LLM Tools MCP Servers

View all →
SkillFM LLM Cost Optimizer

io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage

LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.
Llm Orchestration Agent

io.github.mikerawsonnz/llm-orchestration-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Authenticated Llm Agent

io.github.mikerawsonnz/authenticated-llm-agent

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
Copilot Memory MCP

labforgedev/copilot-memory-mcp

Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
1
Agent Prompt Injection Firewall Mcp

csoai-org/agent-prompt-injection-firewall-mcp

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Authenticated Multi Llm Agent

io.github.mikerawsonnz/authenticated-multi-llm-agent

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f