Audit, pin and diff agent tool lists; preflight and watch remote MCP servers. Free tier; x402.
Scored across 6 tools
The watch family is cleanly split (create/status/cancel), but audit_tools and check_mcp_server overlap substantially: both accept a remote MCP url, both report poisoning patterns, provider compatibility, a grade, and a pin for later diffs. The intended split -- schema/token quality vs. reachability/auth/payment -- is stated in prose but easy to miss, so an agent asked to 'evaluate this MCP server' can plausibly pick either.
Most names use verb_noun (audit_tools, diff_tools, check_mcp_server, watch_mcp_server), but the lifecycle companions flip to a prefix-noun order (watch_status, watch_cancel) instead of status_watch/cancel_watch. The pattern is readable but not uniform.
Six tools map cleanly onto the product's three functions (audit, diff, watch) plus the watch lifecycle, with no filler tools. Nothing feels thin or bloated for this scope.
Audit, diff, and full watch lifecycle (create/status/cancel) are covered, and pins carry state between calls. The main gap is there is no list_watches operation, so a caller who loses a watch_id or secret has no way to enumerate or recover existing watches.
Check the tool definitions an agent loads, before they cost tokens or fail: estimated tokens per tool, schema errors per provider (OpenAI, Anthropic, Gemini, Bedrock, MCP; add openai_strict for strict mode) with JSON paths and fixed definitions, tool pairs models will confuse with fix hints, basic poisoning patterns, a grade and a pin (set_id) for diff_tools. Pass "tools" (array in any common format) or "url" (public remote MCP server; tools are listed, never called). level "lite" returns the summary only. Free: 20 calls/day per IP (shared with diff_tools), then $0.003 lite / $0.01 full via x402 or credits.
Inputs: url, level, tools, providers.
Does this remote MCP server work, and is it worth connecting or paying for? Sends initialize and tools/list only (never calls a tool) and reports reachability, protocol version, sign-in method (OAuth protected-resource metadata), x402 payment terms if it asks for payment, latency, tool count and token cost, provider compatibility, poisoning patterns in tools and server instructions, issues and a grade A-F, plus a pin for later diffs. https public hosts only. Free: 10 checks/day per IP, then $0.005 via x402 or credits.
Inputs: url (required).
What changed in a tool list since you approved it? Compares "tools" or "url" now with "pin" (set_id from audit_tools/diff_tools) or "baseline" (earlier definitions). Each change is labeled breaking (removed tool or param, new required param, type or enum removal), suspicious (new text with injection patterns or hidden characters), review (description, title, annotation or new tool) or additive; descriptions come with before/after text and a word diff. Returns a new pin. Free: 20 calls/day per IP (shared with audit_tools), then $0.002 via x402 or credits.
Inputs: pin, url, tools, baseline.
Free: cancel a watch (no further checks or webhooks; not refunded). Needs watch_id and the secret returned when it was created.
Inputs: secret (required), watch_id (required).
Hosted watch (paid only; this MCP call validates and returns how to pay): ToolFit re-audits a public remote MCP server every 24 h ($0.25) or 6 h ($0.60) for 30 days and POSTs an HMAC-SHA256 signed JSON webhook to your https endpoint when its tools/list fingerprint or grade changes, or it goes unreachable or recovers. Pay at POST /v1/watch or /v1/watch/6h with x402 or a credits key; the response has watch_id and the signing secret (shown once).
Inputs: url (required), webhook (required), every.
Free: state (active, expired, cancelled), interval, expiry, next check, last result (pin, grade, score, tool count) and webhook delivery counters for a watch. Needs watch_id and the secret returned when it was created.
Inputs: secret (required), watch_id (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
MCP Drift Observatory: has a public MCP server's declared tools changed? Free check, archive, feeds.
Free read-only tools for agents: agent-readiness audit, TLS/DNS/header checks, MCP search, utils.
Free agent home and discovery: Clean JSON, advisory Safe Preflight, MCP and x402 tools.
Scan MCP tool definitions for poisoning, look up server history, count tool-list tokens. Free.
Add one secure layer between your agents and this server.
