GroundLens — Claude Code MCP server: what it does, how to install
Fast guardrails MCP server that validates model answers against source passages without external LLM calls.
claude mcp add groundlens -- uvx groundlensWhat GroundLens does
GroundLens checks generated figures and subjects against reference passages. The verification runs in roughly 10 ms via a deterministic Rust engine. It requires no network requests or external model calls for primary checks.
Every run assigns a status of PASS, REVIEW, or FAIL and writes a signed record to disk. Wrong outputs stop here, keeping non-viable answers away from an LLM judge. The server integrates with Langfuse and OpenTelemetry pipelines. Running it requires uvx.
What it helps with
- verify numerical claims against reference text
- catch unsupported statements before querying an LLM judge
- record cryptographically signed logs for validation audits
- stream guardrail telemetry into Langfuse or Grafana
Example prompts for the agent
- Verify this financial summary against the source text using GroundLens
- Check if the numbers in the answer match the provided reference passages
- Run a GroundLens validation and save the decision record
How to install GroundLens
Platform CLI
claude mcp add groundlens -- uvx groundlensuvx runs the command named after the package; if the README names another one, use uvx --from groundlens <command>
Platform CLI
codex mcp add groundlens -- uvx groundlensuvx runs the command named after the package; if the README names another one, use uvx --from groundlens <command>
Config file
{
"mcpServers": {
"groundlens": {
"command": "uvx",
"args": [
"groundlens"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from groundlens <command>
Config file
{
"servers": {
"groundlens": {
"type": "stdio",
"command": "uvx",
"args": [
"groundlens"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from groundlens <command>
Platform CLI
gemini mcp add groundlens uvx groundlensuvx runs the command named after the package; if the README names another one, use uvx --from groundlens <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about GroundLens
How to install GroundLens in Claude Code?
Run claude mcp add groundlens -- uvx groundlens. Make sure uvx is available in your environment.
What does GroundLens do?
It audits AI answers against source documents. The engine flags figure discrepancies and missing support with clear status codes.
Does GroundLens require an API key?
No external API key or online account is needed. The core checks execute locally without model calls.
