Agent Evidence API

Name: Agent Evidence API
Author: thx93

@thx93MCP server · External

MCP-native web evidence and claim verification: cited, source-grounded evidence for AI agents.

Fact-checkingv0.1.5

Freeno charge per call

One address for any MCP client. No sign-in needed on this server.

Safety · AI7%Low risk
Does · AIReadsOnly looks things up
ConnectRemote · no sign-inStreamable HTTP
PopularityNo stars yetUpdated 24 Sep 2026
StatusUnreachableChecked facts, not AI

Overview Tools Trust Requirements Details Similar

What it does

Reads
Writes
High impact

At most: only reads or looks up information.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Tools

None listed · checked 11 Oct 2026

Odel could not list its tools without signing in.

Try it in the Inspector

No README yet. What Odel knows about this module is on the right.

Checked by Odel

Registry verified the namespace io.github.Thx93
The endpoint has not answered since 11 Oct.

Assessed by AIJev

Harmful: 7%
First-party: 25%
High impact: 0%
Adult content: 2%

Read from the listing and README on 11 Oct 2026. AI can make mistakes: a guide, not a check.

Requirements

Runs: Remote, on agent-evidence-api.thx93.workers.dev
Transport: Streamable HTTP
Sign-in: None
Credentials: None asked
Clients: Any MCP client

https://agent-evidence-api.thx93.workers.dev/mcp

The publisher’s server itself; Odel doesn’t run it. Added to your modules, Odel fronts it with one address.

Details

Version: 0.1.5
Updated: 24 Sep 2026
Registry name: io.github.Thx93/agent-evidence-api

Registry listing

Similar modules

Browse Fact-checking

MCP server: One MCP server.
Korean Law MCP
@chrisryugj · External2,658 GitHub stars.
Korean law: statutes, precedents, ordinances, treaties and citation verification (법제처 API).
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Entroly
@juyterman1000 · External474 GitHub stars.
Context Assurance for AI agents: context engineering, AI cost optimization, verification.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
fojin — Buddhist Canon Tools
@fojin · External350 GitHub stars.
Buddhist canon tools: search, passages, cross-canon parallels, dictionaries — all URN-cited.
2% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
2% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
2% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Free Crypto News
@nirholas · External317 GitHub stars.
Free crypto news MCP server — 38 tools, 130+ sources, market data, sentiment, whale alerts & more
7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.Free to use.
7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.Free to use.
7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.Free to use.
MCP server: One MCP server.
Agent Search
@lennney · External111 GitHub stars.
Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
lociRun by its publisher: served from their own domain, namespace checked by the registry.
@ivenkoolab · External100 GitHub stars.
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
3% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
OpenCaseLaw — Swiss Caselaw, Statutes & DoctrineRun by its publisher: served from their own domain, namespace checked by the registry.
@opencaselaw · External72 GitHub stars.
1M+ Swiss court decisions, statutes & doctrine with citation graph (DE/FR/IT). CC0, free, 42 tools.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Web Researcher MCP
@zoharbabin · External66 GitHub stars.
Your AI research assistant that cites real sources and stays honest
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.

MCP server: One MCP server.
Weather
@thx93 · External
US weather for AI agents: active NWS alerts by state, 5-period forecasts by lat/lon. Paid per call.
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 12 Oct.Free to use.
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 12 Oct.Free to use.
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 12 Oct.Free to use.