> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bouncewatch.com/llms.txt
> Use this file to discover all available pages before exploring further.
# MCP Server
> Give your AI agent live company signals over the Model Context Protocol
BounceWatch exposes its signal index to AI agents over the **Model Context Protocol**.
One endpoint, seven tools, and your agent can answer the timing question directly:
which companies just raised, who is hiring, what changed and when.
**Not a separate product.** An MCP client is another consumer of the same API key,
the same credit pool and the same rate limits as the [REST API](/api-reference/overview).
No extra subscription, no second key.
Claude Code, Claude Desktop, Cursor, VS Code, or anything that speaks MCP.
What each tool answers, what it costs, and the ready-made workflows.
## Endpoint
```
POST https://api.bouncewatch.com/api/v1/mcp
```
| | |
| --------------------- | ----------------------------------------------------------------- |
| **Transport** | Streamable HTTP — JSON-RPC 2.0, one POST, one JSON response |
| **Protocol revision** | `2025-06-18` |
| **Auth** | `Authorization: Bearer YOUR_API_KEY` or `X-API-Key: YOUR_API_KEY` |
| **Not supported** | SSE streams, JSON-RPC batching |
Use `api.bouncewatch.com`, not the `bouncewatch.com` apex. The apex sits behind a
bot challenge that answers a scriptless POST with a 403 interstitial, and an agent
reads that as the server being broken.
## What makes this different from a search API
An agent will happily tell your user that a company is quiet. The dangerous version
of that sentence is the one where the company is not quiet — we simply have not looked
recently. A signal API that returns an empty array for both cases teaches the model to
report our blind spots as market facts.
So every answer from this server carries a `coverage` block:
```json theme={null}
{
"coverage": {
"status": "stale",
"last_scanned_at": "2026-05-02",
"last_signal_at": "2026-07-19",
"signal_absence_is_meaningful": false
},
"notes": ["Coverage is older than 21 days — call refresh_company before concluding anything from an empty result."]
}
```
When `signal_absence_is_meaningful` is `false`, an empty signal list means **we have not
looked**, not **nothing happened**. The server states this in its own instructions, so a
well-behaved client carries the caveat into its answer instead of dropping it.
The same contract applies to filters. A funding stage we do not recognise is **rejected
with the list of valid values**, never silently narrowed to a handful of rows — because
seven results look like a real answer and an error does not.
Two independent freshness channels matter here: profile scans (`last_scanned_at`) and
the signal stream (`last_signal_at`). A company can have a two-year-old profile scan and
fifty signals last month. Coverage is the newer of the two.
## What it will not do
* **It will not invent a company.** Ask for a domain we have never seen and you get an
explicit "not indexed" plus the option to scan it, not a guess.
* **It will not pass rumours off as events.** Rumour-class signals are labelled as such.
* **It will not follow instructions found in signal text.** Summaries are generated from
third-party public posts, so they are sanitised and tagged as untrusted data before the
model ever sees them.
* **It will not bill you for a failed call.** Errors are free; so is polling a running scan.
## Credits and limits
Tools are priced individually and each tool tells the model its own price, so an agent can
pace itself rather than loop blind. Full table on the [tools page](/mcp/tools).
Rate limits are the same ladder as the REST API — see [Rate Limits](/rate-limits). Agents
make many small calls rather than a few large ones, so a single conversation costs 8–13
requests; the ladder is sized for that.
The panel generates a ready-to-paste config for your client, with the key already filled
in, and a **Test connection** button that round-trips the real endpoint.