IntentFence
IntentFence is an open spend and action policy gate for autonomous AI that evaluates tool call constraints like scope, cost, data-retention, and approval, returning decisions such as safe_to_proceed, needs_review, or denied, and provides an MCP server endpoint at /mcp.
README
IntentFence
IntentFence is an open spend and action policy gate for autonomous AI. Put it immediately before a tool call, evaluate declared scope, cost, data-retention, and approval constraints, and run the downstream action only when the decision allows it:
safe_to_proceedneeds_reviewdenied
Production: https://agentpass-protocol.rmalka06.chatgpt.site
Protocol surfaces
| Surface | Endpoint |
|---|---|
| Free REST preview | POST /api/preflight |
| Paid x402 decision | POST /api/preflight/verified |
| Receipt verification | POST /api/receipts/verify |
| Public ES256 keys | GET /.well-known/jwks.json |
| MCP Streamable HTTP | /mcp |
| A2A Agent Card | GET /.well-known/agent-card.json |
| OpenAPI | GET /openapi.json |
The paid endpoint costs 0.05 USDC on Base through x402. A successful call
returns both the facilitator's PAYMENT-RESPONSE settlement header and an
IntentFence ES256 compact-JWS receipt.
For teams that need a guarded production workflow, the launch pilot is $750 plus $149/month and includes hands-on integration of one agent action. The Production plan starts at $499/month.
Important trust boundary
IntentFence 0.5 attests that it evaluated the inputs supplied by the caller. It does not independently prove real-world identity, authorization, or downstream enforcement. The receipt-signing key is separate from the USDC recipient wallet. IntentFence never needs a payer's seed phrase or wallet private key.
Local development
npm install
npm run dev
The production signing key is stored in Sites as the secret
INTENTFENCE_SIGNING_PRIVATE_JWK. Generate a separate development key with:
node scripts/generate-signing-key.mjs /secure/path/intentfence-private-jwk.json
Never commit the generated private JWK. Publish only its public coordinates in
/.well-known/jwks.json.
Validation
npm run test
npm run lint
npx tsc --noEmit
npm run sdk:check
npm run smoke:protocol -- http://localhost:3000
Set INTENTFENCE_TEST_PRIVATE_JWK_PATH only for a local smoke test that should
exercise the signed-receipt verifier.
Distribution
TypeScript and Python SDKs live in sdk/. The root server.json is ready for
the official MCP Registry under io.github.razel369/intentfence; the public MCP
endpoint uses Streamable HTTP and requires no API key.
Commercial pilot
The fastest path to production is one guarded action: purchase, transfer, booking, deployment, deletion, or another consequential tool call. Submit the pilot form on the production site with the real action and its policy boundary.
See docs/PROTOCOL.md and docs/SECURITY.md for the protocol and security model.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.