mcpField
A
aipulse

aipulse

Local
github.com/CloudCorpRecordsBusiness & Marketing0Updated 1w ago

About aipulse

aipulse is a local bridge to FalcoScan’s hosted service for AI product and market intelligence. It forwards read-only MCP tools for product lookups, market scores, and verified shutdown or acquisition records.

Key features

  1. 01Look up AI products by name or URL
  2. 02Review opportunity and saturation scores
  3. 03Browse verified shutdowns and acquisitions
  4. 04Compare scored AI markets

Use cases

  1. 01Research an AI product’s market and status
  2. 02Find products that shut down in a given year
  3. 03Review market scores and operating products

MCP support

Exposes FalcoScan’s captured read-only tools to MCP clients and forwards calls to its hosted MCP server, returning results unchanged.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"cloudcorprecords-aipulse": {
"command": "npx",
"args": [
"-y",
"@reneturcios/aipulse"
]
}
}
}
Run commandnpx -y @reneturcios/aipulse

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@reneturcios/aipulse0.1.0
ocighcr.io/cloudcorprecords/aipulse:0.1.0

Tools

4

Saved tool list · updated 2d ago

ParameterTypeRequiredDescription
urlstringNoProduct website, e.g. "cursor.com". Give a name, a url or both.
namestringNoProduct name, e.g. "Cursor".

Details

From the project README

aipulse

aipulse is a small local bridge to FalcoScan's hosted MCP server, which tracks the AI product landscape: which products exist in which markets, how those markets score on opportunity, saturation and wrapper risk, and which products have shut down or been acquired.

The bridge keeps no market data and computes no scores of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. The whole captured surface is read-only: this rebuild adds no write capability.

Tools

  • lookup_product — look up an AI product by name (name), website (url), or both. Returns up to 5 matches with market, operating / shut-down / acquired status (buyer, year and a source), opportunity, saturation and wrapper risk bands, pricing type, free tier, API availability, founding year, headquarters, website and a FalcoScan link. All arguments optional.
  • ai_graveyard — products FalcoScan has verified as shut down or acquired, each with a published source. Optional filters: year, buyer, market. Up to 25 rows per call, newest first.
  • list_markets — every AI market FalcoScan scores, with its public averages (opportunity, saturation, wrapper share, heat), how many products in it are operating, and a link to its market page. No arguments.
  • market_overview — one market in depth: operating product count, public averages, how many of its products shut down or were acquired, and its top 10 operating products with bands. Required: market (a market name or slug).

Configuration

  • FALCOSCAN_MCP_URL (optional) — override the upstream endpoint. Defaults to https://falcoscan.com/api/mcp. (The override hook is this rebuild's own labelled reconstruction.)
  • FALCOSCAN_API_KEY (optional) — when set, every upstream request carries an Authorization: Bearer <key> header. When it is not set, no auth header is sent. (This forwarding is also a labelled reconstruction; the original surface was captured keyless.)
Forwarding mechanics

On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name aipulse), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.

Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with aipulse error: (this rendering is this rebuild's own labelled reconstruction).

CLI

Each tool is also a subcommand taking one JSON argument string (omit it for tools that take none):

npx @reneturcios/aipulse lookup_product '{"name":"Cursor"}'
npx @reneturcios/aipulse ai_graveyard '{"year":2025}'
npx @reneturcios/aipulse market_overview '{"market":"Healthcare"}'
npx @reneturcios/aipulse list_markets
npx @reneturcios/aipulse --version

Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.

MCP server

npx -y @reneturcios/aipulse mcp

MCP client config:

{
  "mcpServers": {
    "aipulse": {
      "command": "npx",
      "args": ["-y", "@reneturcios/aipulse", "mcp"]
    }
  }
}

Docker

docker run -i ghcr.io/cloudcorprecords/aipulse
docker run --rm ghcr.io/cloudcorprecords/aipulse --version

The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.

Development

npm install
npm run build
npm test
npm run dev

The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.

License

MIT — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.