Openclaw Output Vetter MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 173 installs a week from pypi.
Verify AI agent claims vs reality: inline grounding-check + swallowed-exception + transcript review.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 openclaw-output-vetter-mcp -- uvx openclaw-output-vetter-mcp
{
"mcpServers": {
"openclaw-output-vetter-mcp": {
"args": [
"openclaw-output-vetter-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.openclaw-output-vetter-mcp]
command = "uvx"
args = ["openclaw-output-vetter-mcp"]
{
"mcpServers": {
"openclaw-output-vetter-mcp": {
"args": [
"openclaw-output-vetter-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"openclaw-output-vetter-mcp": {
"args": [
"openclaw-output-vetter-mcp"
],
"command": "uvx"
}
}
}
Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.
Identity verification, document checks, sanctions/PEP screening and case review as agent tools.
Grounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).
Verify a vuln report's file/line/function claims against a real GitHub repo.
Verify a vuln report's file/line/function claims against a real GitHub repo.
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.
Answers built from our own checks of this server.