anticonf
Provides web search through DuckDuckGo HTML, enabling the server to find candidate sources for claim verification without requiring API keys.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
anticonf — anti-confabulation MCP server
An MCP server that guards against LLM confabulation structurally: instead of asking a model "is this true?", it fetches raw observed facts and makes the calling model compare its own claim against them.
The design
verify_claimnever returns verdicts like "supports" or "contradicts". It fetches the claimed sources (or searches for candidates), extracts atomic observed facts, and returns them raw. The model that is about to assert does the comparison — against evidence it did not write.note_observationlogs a fact with provenance and returns afact_id. Any citation of an "observation" in an answer should reference this id.Unverified claims surface in
list_observationsas missing entries, so gaps are visible rather than silently filled.v1 makes deliberately no external LLM calls — no scorer that could itself confabulate.
Related MCP server: Recommend Agentic Trust Layer
Tools
Tool | What it does |
| Fetch sources, extract atomic observed facts, aggregate source stats |
| Log a fact with provenance, get back a |
| Recent observations — gives the calling LLM context |
| Fetch one URL (httpx → trafilatura extraction) |
| Wipe the local observations log |
| Translate text |
| Extract JSON from noisy model output |
| Cross-session handoff: post a finding, read recent findings (append-only JSONL) |
Search runs through DuckDuckGo HTML (via ddgs) — no API keys anywhere.
Install
git clone <this repo> && cd anticonf
python3 -m venv .venv && .venv/bin/pip install -r requirements.txtConfigure (any MCP client)
{
"mcpServers": {
"anticonf": {
"command": "/path/to/anticonf/.venv/bin/python",
"args": ["/path/to/anticonf/mcp_server.py"]
}
}
}Data lives in data/observations.jsonl by default; override with the
ANTICONF_DATA_DIR environment variable.
A Rust sibling of this server ships inside
openklawc (crates/mcp-anticonf).
License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.
Real-time fact-check, citation verification, and source-freshness for AI agents.
Verify claims with verdict, confidence & cited sources; batch verify, source checks, daily brief.
Cited web evidence and fact checking for AI agents. $0.01 per call, no API key.
Related MCP Servers
- AlicenseAqualityCmaintenanceVerifies factual claims against live sources and returns a verdict, confidence score, and citations for any agent to use before stating uncertain facts.61MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to verify claims with evidence-based truth scores and confidence levels by running a deterministic pipeline of evidence lanes and adversarial checks.26MIT
- AlicenseAqualityCmaintenanceEnables agents and clients to fact-check factual claims against live web sources, returning citable verdicts with source details and cryptographically signed receipts for downstream verification.161 npmMIT
- AlicenseAqualityCmaintenanceEnables agents to verify real-world assertions like content being posted or PRs merged by fetching live evidence from URLs and GitHub, returning a verified boolean plus raw evidence.35 npmMIT