signalcrest
Registry code: 7a6d278dd61c66fb
Signalcrest scores technology momentum across ten developer and builder communities. Use list_entities for trends aggregated across communities (one row per technology), list_signals for individual posts, and get_entity / get_topic for one trend's or signal's history. Requires a Signalcrest API key sent as `Authorization: Bearer <key>`. Free accounts get 100 requests a month and see the free view (the top 5 signals in full, the rest as locked rows); Relay and Radar keys see everything.
- endpoint
- https://www.signalcrest.app/api/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is signalcrest live?
- Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
- Is signalcrest free to use?
- Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
- What tools does signalcrest have?
- 4 tools: list_signals, get_entity, get_topic, list_entities.
- Is signalcrest safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99.7%· all time 99.7%
last good check
of 4 tools
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- unknown → live
- topic
- developer tools
- used for
- list trending technologies
- get a technology's momentum history
- list top developer community signals
- takes → gives
- text → data
- tools
- 4 reads
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
list_entities reads auth-required 13h ago
Trending entities (products, companies, libraries, technologies) ranked by cross-source momentum. An entity aggregates every post, repo and release mentioning it across ten developer and builder communities — one row per trend rather than per post. Prefer this over list_signals when the user asks about trends or technologies; use list_signals for individual posts.
{ "type": "object", "required": [], "properties": { "limit": { "type": "integer", "maximum": 200, "minimum": 1, "description": "How many entities to return (default 50, max 200)." }, "category": { "enum": [ "ai", "devtools", "security", "web", "data", "crypto", "hardware", "business", "science", "other" ], "type": "string", "description": "Restrict to one category. Omit for all categories." } }, "additionalProperties": false }arguments 29 lineslist_signals reads unknown never probed
Top technology signals ranked by momentum right now, scored every 30 minutes across ten developer and builder communities (Hacker News, GitHub, Stack Overflow, npm, Hugging Face, Dev.to, Lobsters, Product Hunt, arXiv, crypto governance forums). Call this to find what is gaining traction before it reaches search-trend tools — e.g. when the user asks what is emerging, trending, or worth paying attention to in a technology area. Returns live unredacted data with no delay.
{ "type": "object", "required": [], "properties": { "limit": { "type": "integer", "maximum": 200, "minimum": 1, "description": "How many signals to return (default 50, max 200)." }, "category": { "enum": [ "ai", "devtools", "security", "web", "data", "crypto", "hardware", "business", "science", "other" ], "type": "string", "description": "Restrict to one category. Omit for all categories." } }, "additionalProperties": false }arguments 29 linesget_entity reads unknown 13h ago
Full detail for one entity by name (e.g. "kubernetes"): current composite score, complete score history, which communities are talking about it, and the live member items (evidence) behind the score. Names come from list_entities.
{ "type": "object", "required": [ "name" ], "properties": { "name": { "type": "string", "description": "Entity name as returned by list_entities, e.g. \"kubernetes\"." } }, "additionalProperties": false }arguments 13 linesget_topic reads unknown 13h ago
Full detail and complete score history for one topic, by id (e.g. "hn:48910545", "gh:1287845516"). Call this after list_signals to see how a specific signal has moved over time, its cross-source corroboration, and its lifecycle stage. Ids come from list_signals.
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string", "description": "Topic id as returned by list_signals, e.g. \"hn:48910545\"." } }, "additionalProperties": false }arguments 13 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id7a6d278dd61c66fb.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/7a6d278dd61c66fb/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/7a6d278dd61c66fb?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.