Pulse document-extraction API as MCP tools — hosted gateway and local stdio server
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"pulse-mcp-2","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# pulse-mcp [Pulse](https://runpulse.com)'s document-extraction API as an [MCP](https://modelcontextprotocol.io) server — turn PDFs, Office documents, images, and spreadsheets into clean markdown, structured JSON, and tables from Claude Desktop, Cursor, or any MCP client. ## Quickstart You need a Pulse API key (from the [Pulse dashboard](https://runpulse.com)). Add to your MCP client config (Claude Desktop, Cursor, …): ```json { "mcpServers": { "pulse": { "command": "uvx", "args": ["pulse-mcp@latest"], "env": { "PULSE_API_KEY": "<your-pulse-api-key>" } } } } ``` Instead of the env var, the key can live in `~/.pulse/config.toml`: ```toml api_key = "<your-pulse-api-key>" ``` ## Tools | Tool | What it does | |---|---| | `extract` | Document → markdown (chunking, HTML, figure descriptions optional) | | `apply_schema` | Structured JSON from an extraction, against your JSON schema | | `generate_schema` | AI-draft or refine an extraction schema from a prompt | | `extract_tables` | Pull tables (HTML/markdown) out of an extraction | | `split_document` | Partition a document into topic page-ranges | | `batch_extract` | Many documents in one asynchronous batch | | `run_pipeline` | Run a pipeline saved in the Pulse dashboard | | `get_job` | Poll any asynchronous job | `extract` takes a `file_url` — or, because this server runs on your machine, a local `file_path`: the server process reads the file and uploads it out-of-band, so file bytes never pass through the model. Up to 50 MB; pdf, png, jpg, jpeg, bmp, tiff, docx, pptx, xlsx, xlsm, csv, txt, html. ## Hosted alternative Don't want a local process? The same tools are served hosted at `https://mcp.runpulse.com/mcp` (Streamable HTTP) — authenticate with your API key as an `x-api-key` header. ## Links - [Pulse documentation](https://docs.runpulse.com) - [runpulse.com](https://runpulse.com)
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.