LLMVerify

Local-first MCP server for LLM output verification — risk signals, injection and PII checks.

What does this entry provide?

LLMVerify is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 78/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding LLMVerify to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

Source: Official MCP Registry
Quality: 78/100
Install method: npm
Repo: subodhkc/llmverify-npm
Repo updated: Oct 9, 2026

Install command

npx -y llmverify@1.8.0

Install method: npm

Review the upstream source before running this command.

GitHub project

Quality

Repo stars

Repo updated

Oct 9, 2026

How is this score calculated?

Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-10-09T06:49:23.100028Z",
      "publishedAt": "2026-10-09T06:49:23.100028Z",
      "statusChangedAt": "2026-10-09T06:49:23.100028Z"
    }
  },
  "server": {
    "name": "io.github.subodhkc/llmverify",
    "title": "LLMVerify",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "version": "1.8.0",
    "packages": [
      {
        "version": "1.8.0",
        "transport": {
          "type": "stdio"
        },
        "identifier": "llmverify",
        "runtimeHint": "npx",
        "registryType": "npm",
        "packageArguments": [
          {
            "type": "positional",
            "value": "mcp",
            "description": "Run the llmverify MCP stdio server (llmverify mcp subcommand)"
          }
        ],
        "runtimeArguments": [
          {
            "type": "positional",
            "value": "-y"
          }
        ],
        "environmentVariables": [
          {
            "name": "LLMVERIFY_MCP_MAX_INPUT_CHARS",
            "default": "1000000",
            "description": "Max characters accepted in a content/input argument"
          },
          {
            "name": "LLMVERIFY_MCP_TIMEOUT_MS",
            "default": "60000",
            "description": "Per-tool wall-clock timeout in milliseconds"
          },
          {
            "name": "LLMVERIFY_MCP_MAX_OUTPUT_ITEMS",
            "default": "50",
            "description": "Cap on any single output array"
          },
          {
            "name": "LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS",
            "default": "2000",
            "description": "Cap on any single text field in output"
          },
          {
            "name": "LLMVERIFY_HOME",
            "description": "Base directory for engine local state"
          },
          {
            "name": "LLMVERIFY_AUDIT_DIR",
            "description": "Audit JSONL directory"
          },
          {
            "name": "LLMVERIFY_LOG_DIR",
            "description": "Operational log directory"
          },
          {
            "name": "LLMVERIFY_BASELINE_DIR",
            "description": "Drift baseline directory"
          },
          {
            "name": "LLMVERIFY_USAGE_FILE",
            "description": "Usage counter file"
          },
          {
            "name": "LLMVERIFY_AUDIT_HASH_KEY",
            "isSecret": true,
            "description": "Enables keyed hmac-sha256 content hashes in audit records"
          },
          {
            "name": "LLMVERIFY_AUDIT_NO_CONTENT_HASH",
            "description": "Set to 1 to disable content hashes in audit records"
          }
        ]
      }
    ],
    "repository": {
      "url": "https://github.com/subodhkc/llmverify-npm",
      "source": "github"
    },
    "description": "Local-first MCP server for LLM output verification — risk signals, injection and PII checks."
  }
}

Report an issue with this listing