MCP Verify Claim runs on your own machine — the client starts it, so there is no endpoint to ping. 461 installs a week from pypi. Last commit 28 Aug 2026.
Force evidence-gated, tiered claim reporting (FACT/INFERENCE/SPECULATION). No-LLM.
Today is the operative word: we check MCP Verify Claim every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-verify-claim -- uvx mcp-verify-claim
{
"mcpServers": {
"mcp-verify-claim": {
"args": [
"mcp-verify-claim"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-verify-claim]
command = "uvx"
args = ["mcp-verify-claim"]
{
"mcpServers": {
"mcp-verify-claim": {
"args": [
"mcp-verify-claim"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-verify-claim": {
"args": [
"mcp-verify-claim"
],
"command": "uvx"
}
}
}
Local proof facts for AI coding clients: intent, tests, Graph Ops, and review evidence.
FMCSA motor-carrier risk scores, monitoring, and carrier-selection evidence reports for AI agents.
AI Incident Reporting Compliance MCP. Unified classification + reporting-clock tracker across EU...
AI-powered board deck generation and governance reporting for private equity firms.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Report local task-scoped test and build residue without cleaning resources.
Canadian credit: statement-cycle and utilization math, plus bureau and reporting reference data.
Simulated people experience what you are making and report what they noticed and felt.
Answers built from our own checks of this server.