Openclaw Output Vetter Mcp
io.github.temurkhan13Published by GitHub account temurkhan13v1.3.0Updated Oct 27, 2026
Verify AI agent claims vs reality: inline grounding-check + swallowed-exception + transcript review.
The publisher's own server: OpenClaw Direct
Overview
Local MCP server that checks AI agent claims against reality, with inline grounding checks, swallowed-exception detection and transcript review.
- What you can do
- Check whether an agent's claims are grounded in what actually happened.
- Detect swallowed exceptions that hide failures.
- Review agent transcripts for unsupported or inaccurate statements.
- Runs as a local stdio process with no tools listed in the manifest.
- When to use it
- Useful when you want a second check on an AI agent's output before trusting it, for example reviewing transcripts of automated runs or catching errors that were silently suppressed.
- Requirements
- Runs as a local process over stdio, installed from the PyPI package openclaw-output-vetter-mcp, so a Python environment is needed. No authentication, environment variables or headers are declared. Desktop only; not available as a web executable.
Installation
In SourceWeft
- Open Openclaw Output Vetter Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
This repository has no README.
Tools
0Version history
1- v1.3.0LatestSep 16, 2026
Score
25% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.
Other Openclaw integrations
OpenClaw Direct
direct.openclawOfficial publisher
A remote MCP endpoint that lets an assistant deploy, monitor and manage OpenClaw AI assistants through natural language.
OpenClaw MCP Ecosystem
Published by GitHub account yedanyagamiai-cmd
A remote Cloudflare Workers endpoint advertising a bundle of nine MCP servers covering security scanning, knowledge graph, compliance, finance, memory…
Openclaw Upgrade Orchestrator Mcp
Published by GitHub account temurkhan13
A local MCP server for AI runtime upgrade safety, offering snapshot diff and fingerprint checks to detect provider-side regressions.
Openclaw Skill Vetter Mcp
Published by GitHub account temurkhan13
A local MCP server that lets an assistant vet third-party AI agent extensions and agent-configuration files such as AGENTS.md, .cursor/rules and CLAUDE.md.
Openclaw Health Mcp
Published by GitHub account temurkhan13
A local MCP server that reports the health of an OpenClaw deployment, covering gateway, resources, errors, skills, upgrades and disk.