MCP server

Plumbline — a trust layer for LLM answers

com.lattice-sys.plumbline/mcp

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Website

At a glance

Type

MCP server

Publisher

lattice-sys.com (verified by the MCP Registry)

Status

Working at last check

Tools

18

Token cost

About 4,762 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http lattice-sys https://plumbline.lattice-sys.com/mcp/demo

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.lattice-sys]
url = "https://plumbline.lattice-sys.com/mcp/demo"

Gemini CLI

{"mcpServers":{"lattice-sys":{"httpUrl":"https://plumbline.lattice-sys.com/mcp/demo"}}}

Cursor

{"mcpServers":{"lattice-sys":{"url":"https://plumbline.lattice-sys.com/mcp/demo"}}}

VS Code

{"servers":{"lattice-sys":{"type":"http","url":"https://plumbline.lattice-sys.com/mcp/demo"}}}

Antigravity

agy mcp add lattice-sys https://plumbline.lattice-sys.com/mcp/demo

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"lattice-sys","server_url":"https://plumbline.lattice-sys.com/mcp/demo","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"lattice-sys","server_url":"https://plumbline.lattice-sys.com/mcp/demo"}

Tools

• ask_prepare ~647 tokens
  BYO 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 (a signed handoff token; echo it back VERBATIM and in full, or use the short as
• ask_result ~288 tokens
  Fetch 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 connected model you normally never need it: write your draft and call ask_submi
• ask_submit_draft ~380 tokens
  BYO 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 own SQL facts and publishes the trust envelope; a draft that fails any guard is
• compare_departments ~176 tokens
  Compare 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-side); otherwise it returns an explicit refusal, and you should use ask_prepare th
• cross_check ~349 tokens
  Corroborate 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 session to 'corroborated'; DISAGREE marks a CONFLICT (worse than unverified). This i
• describe_fact_capabilities ~118 tokens
  List 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 facts; a route miss is not evidence that the underlying records are absent.
• find_payroll_anomalies ~135 tokens
  Surface 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 server-side); otherwise it returns an explicit refusal, and you should use ask_p
• get_ai_act_transparency ~74 tokens
  Return the Art. 13 transparency descriptor: intended purpose, capabilities, limitations, human oversight, logging mechanism, and article mapping.
• get_answer_queries ~262 tokens
  Show 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, no evidence text, no answer text, no envelope, and no way to list the catalog.
• get_evidence_document ~302 tokens
  Show 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, body, metadata, embedding_text) with the retrieval rank and scores the answer reco
• get_manager_chain ~168 tokens
  Return 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-side); otherwise it returns an explicit refusal, and you should use ask_prepare th
• query_fact ~225 tokens
  Execute 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 reproducible trust receipt containing the dataset and query versions.
• run_code Runs commands · ~488 tokens
  Run 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 code. The raw-SQL server opt-in is enabled, but results still bypass the trust pa
• run_sql ~480 tokens
  Run 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, grounding gate, and answer-facts reconciliation, so results are UNVERIFIED and label
• search_docs ~192 tokens
  Search 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 result set honestly when nothing matches.
• search_employee ~171 tokens
  Search 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 the same call (verified server-side); otherwise it returns an explicit refusal, an
• summarize_benefits ~169 tokens
  Summarize 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 call (verified server-side); otherwise it returns an explicit refusal, and you sh
• trust_finalize ~138 tokens
  Return 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 confidence (k of n figures store-verified, weakest figure tier, conflicts), the p

Browse

• Website monitoring
• Databases
• Running code
• Searching your documents (RAG)

Related MCP servers

• Canal Nav
  Plan canal routes on Great Britain's waterways: lock-aware timing, live closures, boat-fit checks.
• Craigmbrown Blindoracle
  Trust + counterparty-risk layer for x402 A2A trades: reputation, pre-hire check, escrow, disputes
• Criora climate risk
  Climate and disaster risk for any place: warnings, floods, heat, storms, quakes, countries, map
• Macfax
  Identify any Apple serial and read its device record, plus used-Mac prices, listings and checks.
• token-oracle — Token Trust Oracle
  Flags fake/mismatched token contract addresses and hallucinated supply figures before you trade.
• Dataconto: who buys company records and code
  Who pays owners for company records, code and datasets, closed companies included. Sourced terms.
• Sourcey
  Find startup credits and deals; check eligibility and read Agent Readiness reports with evidence.
• holdmark · facts about online stores
  Does this store deliver and refund? Measured with carriers and payment processors.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/com.lattice-sys.plumbline/mcp.svg)](https://aptlynx.net/servers/com.lattice-sys.plumbline/mcp)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents