A verdict per option
Fits, fails or cannot tell, for every requirement, with the value and where it came from.
For AI agents
Coding agents that build on Pulse without guessing the API.
Add the open-source MCP server to Claude Code, Cursor or Codex. The agent searches the current Pulse documentation instead of recalling an endpoint that may not exist, and wires the decision call into whatever it is building.
Where you are
Coding agents remember APIs that changed.
An agent writing an integration from memory invents parameters and endpoints. With the docs one tool call away, it quotes the current reference instead.
The docs, not the agent's memory, are the source of truth.
What happens
How does it work?
One call, from MCP or HTTP. Nothing to train, nothing stored.
- Ask01
State what is needed
As requirements such as "voltage = 24V", or in plain words; a budget in the words becomes a price requirement.
- Send02
Pass the options
Up to 50 at a time, with whatever fields and text you have. A stated field always wins over text read off a page.
- Answer03
Answer from the verdicts
Each option comes back fits, fails or cannot tell, with the attributes that are missing. The agent says what the evidence shows, and only that.
What you get
What the agent gets
"The evidence does not say"
A first-class answer instead of a guess, with the missing attributes named.
A to-do for the owner
Every unknown is exactly what the option's owner should publish next.
MCP or HTTP
The open-source MCP server for agents, or one HTTP call from your own code.
A worked example
In Claude Code: claude mcp add pulse -- npx -y @thepulseapi/mcp. The agent gets four tools: search_docs, get_page, list_pages and resolve_products.
What you get
Before and after
Without the MCP server
- Recalls endpoints from training data
- Guesses request shapes
- Leaves you to check every call
With the MCP server
- Searches the current docs and cites them
- Copies request shapes from the reference
- Can call the decision API with your key
Before you commit
What it will and will not do
What this does
- Give each option a verdict per requirement, grounded in its own evidence
- Name what is missing instead of guessing it
- Work in any domain whose options carry structured attributes
- Answer the same input the same way every time
What it does not do
- State an attribute the evidence never stated
- Read facts out of free text outside laptops yet; send the fields instead
- Make decisions about people, such as hiring or lending
- Promise a business result. Nothing has been measured on your data
Questions
The ones that decide it.
- Does the MCP server send my code anywhere?
- The documentation tools run on your machine and send nothing about your prompts or code. resolve_products sends only its own input to the Pulse API, and only once you set a key.
- Which agents can use it?
- Claude Code, Claude Desktop, Cursor and Codex through the open-source MCP server, which runs on your machine, and any agent or program that can make an HTTP call. ChatGPT's web app needs a remote MCP server, which is planned.
- Is it a model?
- No. It applies rules to the evidence each option states, so the same input always gives the same verdict, and every verdict shows its source.
Add it to your agent.
Install the MCP server with one line, or call the API from your code. The open-source repository has runnable examples.
Opensource
An API key comes from the Pulse dashboard.