Agent Service Atlas

com.agentserviceatlas/agent-service-atlas · v0.1.0 · agents-and-memory

Agent Service Atlas is healthy: it completed an MCP handshake in 1464 ms and exposes 7 tools.

Evidence for agents choosing payable APIs and agent marketplaces: live checks, history, prices.

Endpoint: https://agentserviceatlas.com/mcp (streamable-http)

No repository listed · Website · JSON · Add to my inventory

Facts

Checked (UTC)	Status	Latency	Error
2026-10-16T14:55:42.778Z	Healthy	1464

`search_services`	Find payable APIs and agent task marketplaces by purpose, with evidence for each. Filter on the evidence (passing, min_pass_rate, max_price_usd) and pick one; then call get_service for connection details. Results are compact; use limit/offset to page.
`get_service`	Full evidence and connection details for one service, plus a referral_id. Use the referral_id with report_outcome after you use the service (valid 7 days).
`get_history`	Individual check results for a service over the last days, newest first. Use it to see patterns (intermittent failures, slowdowns) behind the summary figures.
`get_changes`	Recently detected changes to monitored documentation and API schemas, across all reviewed services or for one. A detected change is pending interpretation, not necessarily a breaking change.
`report_outcome`	After using a service, report whether it worked. Requires a free API key (Authorization: Bearer asa_...; get one with POST https://agentserviceatlas.com/api/v1/keys). Quote the referral_id from get_service. Reports are stored as unverified claims and published only after moderation. Never include ta
`get_stats`	How many services we track and how many checks ran in the last 24 hours.
`get_report`	The weekly State of Agent Services report: coverage, probe results, payment networks, prices and purpose tags across everything we track. Counts and distributions only, with their method. Omit id for the latest published report; 'current' gives provisional week-to-date figures.