Toolwork
Server Details
Agent-first tool search. Start with search_tools({job: "your task in plain words"}); free, no key.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
search_tools (discover by task), get_tool (full card for one ID), and report (feedback) target clearly distinct actions. The only soft overlap is that search_tools already returns best_pick/use_it, and get_tool's own description admits it is 'usually not needed', which makes its boundary with search slightly fuzzy.
All three names are snake_case and verb-led (search_tools, get_tool, report), so the convention is readable and predictable. Minor deviation: two use verb_noun while 'report' stands alone as a bare verb.
Three tools is a tight, well-scoped surface for a discovery/recommendation service — search, inspect, and give feedback each earn their place. However, descriptions repeatedly reference a compare_tools tool that is not present in the set, suggesting the surface is slightly under-scoped rather than deliberately minimal.
The core loop (search -> get details -> report outcome) is covered, but compare_tools is referenced as if it exists (report tokens 'cover the first 10 results' from compare_tools) yet is missing, creating a dead reference. There is also no browse/list or category-enumeration path for agents that cannot phrase a concrete job.
Available Tools
3 toolsget_toolARead-onlyIdempotentInspect
Full Agent Tool Card for one ID (usually not needed: search_tools already returns best_pick.use_it to set it up). Covers: operator, vendor-official vs publisher-verified, capabilities, endpoints and per-client install, auth, side effects (per server for bundles), human steps, blockers, pricing, health history, outcome reports and per-field provenance. Unknown IDs return isError with error_code not_found.
Inputs: id (required), stage, client, agent_type.
reportAInspect
PREFERRED way to give feedback, using the top-level report_token from search_tools/get_tool/compare_tools (covers the first 10 results, valid 30 days). Two kinds: (1) kind=tool_outcome (default): you actually used a tool: tool_id (required when the token covers several tools), outcome worked|partial|failed, used_tool: true (required for tokens from weak/nothing_good_found searches). (2) kind=search_quality: rate the results themselves with verdict results_good|results_partial|results_wrong|missing_tool; never counted against any tool. Note max 300 chars. Reuse your contributor_key.
Inputs: report_token (required), kind, note, stage, +8 more.
search_toolsARead-onlyIdempotentInspect
Call this FIRST when you need a tool, API, SDK, CLI or MCP server for a task you can't do yet: describe the task in plain words (job) and get one best_pick with a paste-ready use_it snippet (MCP client config JSON, install command, or API base URL + docs). One call is usually enough: best_pick.summary says in one line what to use and why (reasons: vendor-official or third-party, live check, auth, read-only or can send/spend, outcome reports), best_pick.report_call is the one-line report to send after you use it; results lists ranked alternatives with score breakdowns (evidence, source URL, date), side effects and human steps; verdict is honest (good_match / weak_matches / nothing_good_found / cannot_work_as_asked / not_a_tool_job, then best_pick is null and answer says why; not_a_tool_job adds a curated workaround). Constraints written in the job ('no account', 'nothing paid', 'no new token scopes', 'headless') or in constraints are checked per result (constraint_check). Free, no key. Returns a top-level report_token for optional feedback.
Inputs: job (required), stage, client, detail, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Free search across ~35,000 agent tools (x402 bazaar + MCP registry) by plain-language need.
Discover, inspect and run 63,000+ agent tools from one balance. Pay per call, no subscriptions.
One key and one prepaid balance for 3,051 pay-per-call tools from 99 providers for AI agents: search, maps, shopping, market data, web pages, images and more. Agents find tools by job, see the price before running, and pay per call. Failed calls are free. Sign in with OAuth, no API key to copy. Sign-up is open to everyone.
Free search over ~50k agent tools: paid x402 APIs and MCP servers. Price, networks, how to call.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceSearch and discover 500+ tools, APIs, and services for AI agents. Browse 15 categories, get recommendations, and access structured metadata including auth methods, free tiers, and example calls.1-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to find the right tool from a vague, misspelled, or rambling description by searching a library of tools and returning ranked matches with fit grades, links, and evidence.1MIT
- FlicenseNot gradedqualityCmaintenancePay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.-
- FlicenseAqualityDmaintenanceEnables autonomous task execution by dynamically searching APIs, generating Python tools, and running them on-demand, with built-in web search, scraping, and file operations.3-
Glama MCP Gateway
Add one secure layer between your agents and this server.