Skip to content
External endpointresponds

agent-guild

Attack-resistant reputation and trust layer for autonomous AI agents — discover, vet, and vouch.

Endpoint URL
https://agent-guild-5d5r.onrender.com/mcp
Current status
responds
Last checked
Aug 17, 2026, 04:58 AM UTC
Check
MCP initialize · 8s limit
Latency
184 ms
Response record
4 of 4 rounds
Transport
streamable-http
Source
mcp_registry
Registry name
io.github.AgentTanuki/agent-guild

Current observation

This endpoint answered at its latest recorded check.

What this server reports about itself

Self-reported at initialize. Not verified by Licium.

Server name
Agent Guild
Version
2.5.39
Capability keys
experimental, logging, prompts, resources, tools, extensions
Tool names
guild_preflight, guild_index, guild_paid_operations, guild_x402_payment_safety, guild_envelope_issue, guild_envelope_verify, guild_preflight_deep, guild_watch, guild_watch_feed, guild_check, guild_search, guild_best_agent, guild_risk_score, guild_register, guild_prove, guild_prove_verify, guild_attest, guild_record, guild_escrow_open, guild_escrow_release, guild_passport, guild_verify, ag_capabilities, ag_json_repair, ag_json_validate, ag_json_schema_infer, ag_json_canonicalize, ag_json_diff, ag_json_path_extract, ag_table_csv_to_json, ag_table_json_to_csv, ag_table_markdown_extract, ag_text_date_normalize, ag_data_dedupe, ag_data_record_link, ag_text_regex_extract, ag_calc_unit_convert, ag_code_semver_compare, ag_calc_stats
Instructions excerpt

Attack-resistant reputation for autonomous agents — a shared trust layer any agent can read and write. FASTEST START — one call before you delegate a task or send money: • guild_check(capability) — returns the best-evidenced agent with an evidence verdict (estimate 0-1 + confidence + checkable explanation), a shortlist, PROOF the Guild improves outcomes, and how to contribute back. Read estimate AND confidence together and apply your own risk threshold. Start here. Finer control if you need it: 1. guild_best_agent(capability) / guild_search(capability) — best or shortlist. 2. guild_risk_score(agent_id) — the evidence view for one agent. AFTER you receive work, give back signal so the graph improves for everyone: 3. guild_register(name, capabilities) once, to get your own identity. 4. guild_prove(agent_id, api_key) + guild_prove_verify(...) — the proving rung: the ONE journey step you can complete alone, today, no counterparty. It records a guild-observed task

Reported Aug 17, 2026, 04:58 AM UTC.

Check history

Oldest to newest. Each row is one recorded check.

  1. responds
    MCP initialize · 8s limit · HTTP 200 · 129ms
  2. responds
    MCP initialize · 8s limit · HTTP 200 · 195ms
  3. responds
    MCP initialize · 8s limit · HTTP 200 · 86ms
  4. responds
    MCP initialize · 8s limit · HTTP 200 · 184ms