Agents Index

Plumbline — a trust layer for LLM answers

Online

Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason.

Visit publisherConnectJSON

What it can do: 18 tools

  • ask_prepare read-onlyBYO step 1 of 2: run the server-side trust plane for a business question (plan, SQL-verified facts, evidence retrieval, answerability gate, prompt composition) and return the composed prompt plus a single-use prepare_key
  • ask_result read-onlyFetch the published verdict for an ask_prepare session (status: pending, published, or unknown). This is the app panel's polling surface, so the verified answer renders inside the panel that prepared the question. As the
  • ask_submit_draft read-onlyBYO step 2 of 2: verify the draft you wrote for an ask_prepare prompt. The server runs the SAME post-answer guards the strict path uses (facts presence, tagged claims, concept binding, earner-name grounding) against its
  • compare_departments read-onlyCompare two departments by headcount and compensation. NOTE: internal drafting is disabled on this deployment. If your client supports MCP sampling, this tool asks YOUR model to draft in the same call (verified server-si
  • cross_check read-onlyCorroborate a figure you obtained (e.g. from run_sql) against the verified fact store: it re-derives the named value_key from the same SQL the verified pipeline uses and compares. AGREE lifts an otherwise-unverified sess
  • describe_fact_capabilities read-onlyList safe metadata for the registered fact queries available on the server-pinned dataset: IDs, labels, parameters, and result shapes, never SQL. Use this when a question appears relevant but a selected route produced no
  • find_payroll_anomalies read-onlySurface payroll and deduction anomalies in the latest snapshot. NOTE: internal drafting is disabled on this deployment. If your client supports MCP sampling, this tool asks YOUR model to draft in the same call (verified
  • get_ai_act_transparency read-onlyReturn the Art. 13 transparency descriptor: intended purpose, capabilities, limitations, human oversight, logging mechanism, and article mapping.
  • get_answer_queries read-onlyShow the SQL behind one answer you already received, addressed by its correlation_id. Returns only the recorded fact queries (id, version, label, SQL, parameters, result schema, dataset version) for that answer: no rows,
  • get_evidence_document read-onlyShow ONE retrieved evidence document behind an answer you already received, addressed by that answer's correlation_id plus a document_id from its evidence_documents references. Returns the full stored document (title, bo
  • get_manager_chain read-onlyReturn the management/reporting chain for an employee. NOTE: internal drafting is disabled on this deployment. If your client supports MCP sampling, this tool asks YOUR model to draft in the same call (verified server-si
  • query_fact read-onlyExecute a registered, versioned read-only fact query against the server-pinned dataset. Provide query_id and version only: SQL is approved by the domain pack, never caller-supplied. Returns normalized rows plus a reprodu
  • run_code read-onlyRun YOUR OWN JavaScript in the in-tenant coderunner sandbox with the read-only, snapshot-scoped plumb.query() SDK. No filesystem, environment, or general network access. Read plumbline://sandbox-api.d.ts before writing c
  • run_sql read-onlyRun YOUR OWN single read-only SELECT/WITH over the virtual snapshot_* relations. The query is statically verified against an allowlist, rewritten to the active snapshot, and run read-only. This BYPASSES the planner, grou
  • search_docs read-onlySearch Plumbline's own product and architecture documentation (how the verification, refusal, and trust layer itself works). Returns ranked, citable doc passages; does NOT touch employment data, and returns an empty resu
  • search_employee read-onlySearch the employment fact store for a person and return a grounded, verified answer. NOTE: internal drafting is disabled on this deployment. If your client supports MCP sampling, this tool asks YOUR model to draft in th
  • summarize_benefits read-onlySummarize benefit enrollments, optionally scoped (e.g. a department or plan). NOTE: internal drafting is disabled on this deployment. If your client supports MCP sampling, this tool asks YOUR model to draft in the same c
  • trust_finalize read-onlyReturn the session's graded trust verdict: the tier (verified / registered-query / generated-sql / corroborated / unverified / conflict / refused), which trusted steps were skipped across the session, the deterministic c

Connect it

Claude Code
claude mcp add --transport http plumbline-a-trust-layer-for-llm-answers https://plumbline.lattice-sys.com/mcp/demo
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://plumbline.lattice-sys.com/mcp/demo
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "plumbline-a-trust-layer-for-llm-answers": {
      "url": "https://plumbline.lattice-sys.com/mcp/demo"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "plumbline-a-trust-layer-for-llm-answers": {
      "type": "http",
      "url": "https://plumbline.lattice-sys.com/mcp/demo"
    }
  }
}

Questions

What does Plumbline — a trust layer for LLM answers do?

Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason. It exposes 18 tools to AI assistants.

What tools does Plumbline — a trust layer for LLM answers provide?

18 tools, including ask_prepare, ask_result, ask_submit_draft, compare_departments, cross_check, describe_fact_capabilities, find_payroll_anomalies, get_ai_act_transparency, get_answer_queries, get_evidence_document, get_manager_chain, query_fact….

How do I connect Plumbline — a trust layer for LLM answers to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://plumbline.lattice-sys.com/mcp/demo as a custom connector or MCP server. Copy-paste setup is on this page.

Does Plumbline — a trust layer for LLM answers require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Plumbline — a trust layer for LLM answers online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Plumbline — a trust layer for LLM answers?

plumbline.lattice-sys.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Databases & Data