Plumbline — a trust layer for LLM answers is a remote MCP server that gives an AI agent 18 tools, among them ask_prepare, ask_result, ask_submit_draft. It answers at https://plumbline.lattice-sys.com/mcp/demo over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ask_prepare | 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 t Inputs: history, original_question, question |
ask_result | 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 Inputs: include_prompt, prepare_key |
ask_submit_draft | 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 pu Inputs: decline_reason, model, prepare_key, raw_answer |
compare_departments | 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 re Inputs: a, b |
cross_check | 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 Inputs: value, value_key |
describe_fact_capabilities | 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 |
find_payroll_anomalies | 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); otherw |
get_ai_act_transparency | Return the Art. 13 transparency descriptor: intended purpose, capabilities, limitations, human oversight, logging mechanism, and article mapping. |
get_answer_queries | 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, n Inputs: correlation_id |
get_evidence_document | 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, embedd Inputs: correlation_id, document_id |
get_manager_chain | 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 re Inputs: employee |
query_fact | 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 Inputs: parameters, query_id, version |
run_code | 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 ser Inputs: acknowledge_unverified, code, concepts |
run_sql | 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 answ Inputs: acknowledge_unverified, concepts, sql |
search_docs | 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 Inputs: limit, query |
search_employee | 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 (verifie Inputs: query |
summarize_benefits | 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 Inputs: scope |
trust_finalize | 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 fi |
Every block below points at https://plumbline.lattice-sys.com/mcp/demo. Pick your client and copy.
claude mcp add --transport http plumbline-a-trust-layer-for-llm https://plumbline.lattice-sys.com/mcp/demo
{
"mcpServers": {
"plumbline-a-trust-layer-for-llm": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://plumbline.lattice-sys.com/mcp/demo"]
}
}
}{
"mcpServers": {
"plumbline-a-trust-layer-for-llm": {
"url": "https://plumbline.lattice-sys.com/mcp/demo"
}
}
}{
"servers": {
"plumbline-a-trust-layer-for-llm": {
"type": "http",
"url": "https://plumbline.lattice-sys.com/mcp/demo"
}
}
}{
"context_servers": {
"plumbline-a-trust-layer-for-llm": {
"url": "https://plumbline.lattice-sys.com/mcp/demo"
}
}
}{
"mcpServers": {
"plumbline-a-trust-layer-for-llm": {
"serverUrl": "https://plumbline.lattice-sys.com/mcp/demo"
}
}
}{
"mcpServers": {
"plumbline-a-trust-layer-for-llm": {
"url": "https://plumbline.lattice-sys.com/mcp/demo"
}
}
}name: Plumbline — a trust layer for LLM answers
version: 0.0.1
schema: v1
mcpServers:
- name: Plumbline — a trust layer for LLM answers
type: streamable-http
url: https://plumbline.lattice-sys.com/mcp/demo{
"mcpServers": {
"plumbline-a-trust-layer-for-llm": {
"httpUrl": "https://plumbline.lattice-sys.com/mcp/demo"
}
}
}{
"mcpServers": {
"plumbline-a-trust-layer-for-llm": {
"type": "http",
"url": "https://plumbline.lattice-sys.com/mcp/demo"
}
}
}{
"mcpServers": {
"plumbline-a-trust-layer-for-llm": {
"url": "https://plumbline.lattice-sys.com/mcp/demo"
}
}
}goose://extension?url=https%3A%2F%2Fplumbline.lattice-sys.com%2Fmcp%2Fdemo&type=streamable_http&id=plumbline-a-trust-layer-for-llm&name=Plumbline%20%E2%80%94%20a%20trust%20layer%20for%20LLM%20answers
It answered our last check on 18 October 2026 in 536 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by lattice-sys.com and served from plumbline.lattice-sys.com, the vendor's own domain: https://plumbline.lattice-sys.com/mcp/demo.
18, as returned by the server's own tools/list on 31 August 2026: ask_prepare, ask_result, ask_submit_draft, compare_departments, cross_check, describe_fact_capabilities, find_payroll_anomalies, get_ai_act_transparency, and 10 more.
It answered our last check on 18 October 2026 in 536 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://plumbline.lattice-sys.com/mcp/demo. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.lattice-sys.plumbline. Endpoint host: plumbline.lattice-sys.com. ARD identifier: urn:air:com.lattice-sys.plumbline:mcp:mcp.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.