MCP observability and control plane — audit logging, rate limiting, circuit breaker for any MCP server
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-warden","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# 👁️ mcp-warden **MCP observability and control plane.** ```bash pip install mcp-warden mcp-warden audit -- your-mcp-server [args...] mcp-warden guard --max-calls-per-minute 30 --block-tool write_query -- any-mcp-server mcp-warden both --max-calls-per-minute 60 --max-response-kb 512 -- any-mcp-server mcp-warden log --tail 20 ``` [](https://pypi.org/project/mcp-warden/) [](https://www.python.org/) [](LICENSE) [](https://github.com/raj8github/mcp-warden/actions) []() --- ## The problem MCP clients like Cline and Claude Desktop can call tools on any connected server with no visibility and no throttle. An agent in a loop can: - Call `sql_query` hundreds of times a minute, burning your API budget - Pull back 50 MB of data in a single tool call - Hit a tool you meant to leave off - Fail repeatedly and nobody notices until the damage is done mcp-warden fixes all of this — for **any** MCP server, without touching it. --- ## How it works ``` MCP client (Cline / Claude Desktop) │ stdin/stdout ▼ mcp-warden ◄──── audit + guard │ subprocess stdin/stdout ▼ Upstream MCP server (any MCP server) ``` mcp-warden is a transparent JSON-RPC relay. The client never knows it's there. The upstream server never knows it's there. Every `tools/call` passes through the audit and guard layer in the middle. **Latency impact:** ~0.1–0.5 ms per message — negligible against typical LLM tool call round trips of 100 ms to 10 s. --- ## Install ```bash pip install mcp-warden ``` Zero runtime dependencies. Pure Python 3.9+ stdlib. --- ## Usage ### Audit — log everything ```bash mcp-warden audit \ --audit-…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.