Signal Bureau is a remote MCP server that gives an AI agent 22 tools, among them ask, create_order, get_account. It answers at https://api.signalbureau.ai/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
SigB (Signal Bureau): maintained, source-traced record of entities and events in your named domain.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ask | Ask what the tracked record shows about a named entity or unfolding event: what changed, what the record holds now, and which sources corroborate it. Not general knowledge or history — grounding is live tracked coverage. Costs one Read on a Inputs: question, fresh |
create_order | Assemble a basket and get exact prices plus Stripe checkout links. Checkout runs on Stripe's hosted page, completed by whoever holds the payment credentials. Pass dryRun:true to REHEARSE: same validation, same price math, clearly labeled, n Inputs: items, quoteId, topics, email, dryRun, idempotencyKey |
get_account | Your meter-account statement, live: month-to-date metered Reads counted at the published tariff, your watched topics with billing/billing status and their acceptance evidence, and your daily cap. Requires your identified key on the request |
get_answer | Collect an async answer by ticketId (from ask). Free and unmetered — the work was paid for once at submit. status:'working' → poll again after pollAfter seconds; 'done' → the complete answer rides in this response; 'failed' or 'lost' → the Inputs: ticketId |
get_calibration | Deprecated: this tool is winding down — for evaluating or reading the maintained record, use get_truth_object, get_entity/search_entities, and todays_brief instead. Still served here: the grading dataset for the market sensor we cite, and o |
get_corroborated | What independent sources agreed on in the published window — the maintained record's corroboration layer. Each event carries the claim as its sources state it, the corroboration tier, how many INDEPENDENT origins reported it (a wire republi Inputs: limit, tier |
get_desk_feed | A newsletter DESK's machine feed at one predictable, slug-addressable location: up to 14 days of the desk's observed items (title, url, source), newest-first, from the same panel the human edition reads. Unlike watch topics, the desk roster Inputs: desk, days |
get_entity | Full dossier for one entity: signal count, verticals it's spreading across, and why it's surfacing. Inputs: name |
get_events | Tracked world events (situations, races, negotiations) the engine follows as named arcs — each with its entities, related market-question count, cross-domain mention volume, and first/last-seen dates. Optional query filters by name or entit Inputs: query, limit |
get_feedback_status | The state of a report you filed via send_feedback, by its feedbackId: filed, working, or resolved — with its work-order reference. A report filed in the last few hours may still read 'filed'; the response states where it is. Inputs: feedbackId |
get_order | Re-read an order intent created by create_order — the recorded basket and its honest status. Payment truth for checkout purchases lives with Stripe (the payer's receipt is authoritative); metered work is receipted on your meter account and Inputs: order_id |
get_quote | Feed in your requirements — free-form concerns, questions, whole areas of interest — and get back an enumerated quote: your requirements intelligently grouped and disambiguated into well-formed watched topics, each priced flat from the publ Inputs: requirements |
get_record | Deprecated: this tool is winding down — for evaluating or reading the maintained record, use get_truth_object, get_entity/search_entities, and todays_brief instead. Still served here: the correction record — the flagged-vs-control repricing |
get_signals | START HERE for browsing — the cheap read (500/day, no model work). The full machine-readable signal feed (same payload as GET /api/signals): every entity currently flagged by the attention engine, with trajectory, domains, desk membership, Inputs: limit, direction |
get_truth_record | The maintained record for one subject — the ONE file its /exhibit page renders from and GET /api/truth/{slug} serves, so their numbers agree by construction and a value-parity gate fails the build if they stop: what the subject is, the firs Inputs: subject, topic |
get_watch_feed | The structured daily delivery for a machine-watched topic: up to 14 days of observed items (title, url, source, date) newest-first, plus the topic's live coverage-acceptance report, which grades the coverage and shows the evidence (it does Inputs: topic, days |
propose_topic | Propose NET-NEW coverage — a topic, entity, or standing question we don't track yet. Files into the coverage-request queue humans review; accepted topics enter the provisional coverage lane and start appearing in the signal feed. Needs your Inputs: topic, email, why, requester |
search_entities | Find tracked entities/topics by name or vertical (e.g. 'iran', 'semiconductors'). Inputs: query |
send_feedback | File structured feedback with the desk: a bug, an improvement, a complaint, praise, or a question about the service itself. Free, no contact details required; limits stated up front: 5/minute, 20/day per network address (shared egress share Inputs: kind, summary, detail, about, ref |
start_here | START HERE — first call, no arguments, no key, no charge. Who Signal Bureau is and what we are not, the tests you can run to check that claim yourself, what is free (most of it), what is paid (Watches and Reads) at live published prices, ho |
todays_brief | Today's morning brief — the daily synthesized narrative of what moved across the information environment and what to watch, from the engine's cross-domain analysis. Same content as the public /today page. |
top_accelerating | The entities/topics accelerating most across the information environment right now, ranked by cross-domain attention. Inputs: limit |
Every block below points at https://api.signalbureau.ai/api/mcp. Pick your client and copy.
claude mcp add --transport http signal-bureau https://api.signalbureau.ai/api/mcp
{
"mcpServers": {
"signal-bureau": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.signalbureau.ai/api/mcp"]
}
}
}{
"mcpServers": {
"signal-bureau": {
"url": "https://api.signalbureau.ai/api/mcp"
}
}
}{
"servers": {
"signal-bureau": {
"type": "http",
"url": "https://api.signalbureau.ai/api/mcp"
}
}
}{
"context_servers": {
"signal-bureau": {
"url": "https://api.signalbureau.ai/api/mcp"
}
}
}{
"mcpServers": {
"signal-bureau": {
"serverUrl": "https://api.signalbureau.ai/api/mcp"
}
}
}{
"mcpServers": {
"signal-bureau": {
"url": "https://api.signalbureau.ai/api/mcp"
}
}
}name: Signal Bureau
version: 0.0.1
schema: v1
mcpServers:
- name: Signal Bureau
type: streamable-http
url: https://api.signalbureau.ai/api/mcp{
"mcpServers": {
"signal-bureau": {
"httpUrl": "https://api.signalbureau.ai/api/mcp"
}
}
}{
"mcpServers": {
"signal-bureau": {
"type": "http",
"url": "https://api.signalbureau.ai/api/mcp"
}
}
}{
"mcpServers": {
"signal-bureau": {
"url": "https://api.signalbureau.ai/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.signalbureau.ai%2Fapi%2Fmcp&type=streamable_http&id=signal-bureau&name=Signal%20Bureau
It answered our last check on 22 October 2026 in 709 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
22, as returned by the server's own tools/list on 14 September 2026: ask, create_order, get_account, get_answer, get_calibration, get_corroborated, get_desk_feed, get_entity, and 14 more.
It answered our last check on 22 October 2026 in 709 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.signalbureau.ai/api/mcp. 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: io.github.evolutionlabs-dev. Endpoint host: api.signalbureau.ai. ARD identifier: urn:air:io.github.evolutionlabs-dev:mcp:signal-bureau.
First indexed 10 September 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.