{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_qhazba2texgc","handle":"mcp-tollbooth","url":"https://wellknown.network/agents/mcp-tollbooth","links":{"self":"https://wellknown.network/agents/mcp-tollbooth/record.json","html":"https://wellknown.network/agents/mcp-tollbooth","markdown":"https://wellknown.network/agents/mcp-tollbooth/record.md","api":"https://wellknown.network/api/v1/agents/mcp-tollbooth","status":"https://wellknown.network/api/v1/agents/mcp-tollbooth/status","claim":"https://wellknown.network/agents/mcp-tollbooth/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-tollbooth/claim.json","badge":"https://wellknown.network/agents/mcp-tollbooth/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-tollbooth/history","tools":"https://wellknown.network/api/v1/agents/mcp-tollbooth/tools"},"ard":{"identifier":"urn:air::server:mcp-tollbooth","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-tollbooth","summary":"A security gateway for AI agents: a transparent MCP proxy that enforces policy, DLP, and audit on every tool call and result.","description":"<p align=\"center\">\n  <img src=\"https://raw.githubusercontent.com/Realgagenichols/tollbooth/main/assets/header.svg\" alt=\"tollbooth — a firewall + DLP + audit layer for AI agent tool traffic\" width=\"860\">\n</p>\n\n<p align=\"center\">\n  <a href=\"#\"><img alt=\"Python 3.12+\" src=\"https://img.shields.io/badge/python-3.12%2B-3776AB?logo=python&logoColor=white\"></a>\n  <a href=\"#\"><img alt=\"Built on MCP\" src=\"https://img.shields.io/badge/built%20on-MCP-58A6FF\"></a>\n  <a href=\"#development\"><img alt=\"674 tests\" src=\"https://img.shields.io/badge/tests-674%20passing-3FB950\"></a>\n  <a href=\"#design-decisions-that-matter\"><img alt=\"Fail-closed by default\" src=\"https://img.shields.io/badge/default-fail--closed-F85149\"></a>\n  <a href=\"https://github.com/Realgagenichols/tollbooth/blob/main/LICENSE\"><img alt=\"MIT license\" src=\"https://img.shields.io/badge/license-MIT-8957E5\"></a>\n</p>\n\n<p align=\"center\">\n  <b>tollbooth</b> sits between any MCP client and the servers it talks to, and enforces\n  security policy, data-loss prevention, and a tamper-evident audit trail on\n  <i>every</i> tool call and result that crosses the boundary.\n</p>\n\n---\n\nYour AI agent's tool traffic — filesystem writes, shell exec, web fetches, API calls — flows **unmediated** today. There is no control point to deny a dangerous call, stop a secret from leaking out through a tool argument, redact a credential before it lands in the model's context, or produce a compliance-grade record of what the agent actually did.\n\ntollbooth is that control point. It's a transparent [MCP](https://modelcontextprotocol.io) proxy: your client points at one server (tollbooth), tollbooth wraps the real upstream servers, and the gateway config file *is* the security boundary.\n\n## Caught in the act\n\nA single config turns an unmediated agent into a governed one. The recording below is **real `tollbooth` output** — every frame is the live policy + DLP engine answering actual Claude Code hook events (reproduce it yourself with `vhs demo/demo.t…","publisher":null,"homepage":"https://github.com/Realgagenichols/tollbooth","repository":"https://github.com/Realgagenichols/tollbooth","version":"0.4.0","license":null,"protocols":["mcp"],"tags":["ai-agents","audit","dlp","gateway","mcp","model-context-protocol","proxy","security"],"pricing":null,"endpoints":[{"url":"pypi:mcp-tollbooth","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.filesystem","name":"Filesystem","confidence":0.882,"provenance":"derived"}],"categories":["dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-tollbooth","registry":"pypi","observedAt":"2026-11-03T16:26:08.743Z","publishedAt":"2026-10-04T03:02:06.082447Z","latestVersion":"0.4.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-tollbooth","url":"https://pypi.org/project/mcp-tollbooth/","firstSeenAt":"2026-09-10T05:21:19.867Z","fetchedAt":"2026-11-03T16:25:12.737Z","normalizedAt":"2026-11-03T16:25:12.737Z"}]},"firstSeenAt":"2026-09-10T05:21:19.867Z","updatedAt":"2026-11-03T16:26:08.743Z"}