GroundLens
Guardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.
Connector by groundlens-dev · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/groundlens-dev-groundlens
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: llm-evaluation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.
- Tools
- 3 read · 0 write · 0 deleteRead-only
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Tools by what they do 3
Read from the source code; the running server may list different tools.
Read 3 · Look things up without changing anything.
verify_answerverify_recordsverify_run
Network hosts it talks to 3
github.com· found in codeglama.ai· found in codegroundlens.dev· found in code
Tools (3)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
verify_answerVerify an answerCheck an answer against the passages it was written from, before you send it. Every figure must be in the passages or follow from figures that are; no model is used. Returns PASS, REVIEW or FAIL with the reasons, and the signed record. sources: (id, text) pairs, {"id","text","provenance"} dicts, or bare strings. policy: a built-in name (e.g. "eu_ai_act_high_risk_v1"), a path, or YAML. scope: what the request is about, e.g. {"entity": "UPS"}; a figure taken from a source whose provenance is another entity fails. risk_class: the request's risk class, when the policy defines them. Returns the d…
verify_recordsVerify a records logVerify a log of records offline: every hash, every link, every signature. records: the JSON Lines text of an answer-record or run-record log. Returns {"ok", "verified", "kind"}; fails if any record or link was altered.
verify_runVerify an agent runVerify an MCP execution trace under an execution policy and return the run record. trace: the MCP session as JSON-RPC messages (JSON Lines). policy: the execution policy, as YAML/JSON text or a path. Returns the gate (ALLOW/REVIEW/DENY), any breaches, and the signed run record.
Compare and alternatives
Featured in
Signals
- Stars
- 7
- Forks
- 4
- Open issues
- 0
- Weekly downloads
- 318
- Last commit
- Oct 19, 2026 (9 days ago)
- Last release
- Oct 16, 2026 (12 days ago)
- Last package publish
- Oct 16, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.groundlens-dev/groundlens- Version
- 6.0.5
- Auth
- No auth
- Packages
- pypi groundlens
- License
- Apache-2.0
- Repository
- github.com/groundlens-dev/groundlens
- Website
- groundlens.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
GroundLens MCP server. Agent Mart. https://agentmart.dev/connectors/groundlens-dev-groundlens (last updated 2026-10-24)