# jitprompt

> jitprompt is an MCP server for agent instructions. Upload your docs as they are; jitprompt splits them into sections and serves your agent a live table of contents plus only the sections each turn needs, instead of one giant system prompt.

Sign up free at https://app.jitprompt.com/ui/signup; Starter and Pro are chosen in the app (Plan & usage).

## How it works

- Upload Markdown, plain text, PDF or Word files as they are. jitprompt splits each document into titled, summarized sections (a model is used once, at ingest — never on search).
- Your agent connects over MCP (streamable HTTP, bearer API key bound to one namespace) at https://app.jitprompt.com/mcp.
- Three tools: `get_toc` (a live table of contents of every document), `get_section` (open a section by id), `search_instructions` (search by what the agent is about to do; returns whole sections).
- jitprompt's own docs are served the same way at https://app.jitprompt.com/mcp/docs, to any API key: https://docs.jitprompt.com/connect-your-agent/docs-mcp/

```sh
claude mcp add --transport http jitprompt https://app.jitprompt.com/mcp --header "Authorization: Bearer imcp_…"
```

## Plans

- **Free** — $0: 1 namespace; 3 documents per namespace; 5 ingestions per day, per organization; Documents up to 50,000 characters; Current version only · no search sandbox
- **Starter** — $4.99/month: 3 namespaces; 10 documents per namespace; 10 ingestions per day, per organization; Document version history; Search sandbox
- **Pro** — $49.99/month: 10 namespaces; Unlimited documents; 100 ingestions per day, per organization; Document version history; Search sandbox

## FAQ

### How is this different from RAG over my docs?

Three ways. Search is driven by what the agent is about to do, not by the user's message. Results are whole sections, never fragments. And the agent always sees a map of what exists, so it can go straight to a section instead of hoping a search finds it.

### Do I have to restructure my docs?

No. Upload Markdown, plain text, PDF or Word files as they are. jitprompt splits them into sections, titles and summarizes each one, and you can review every section in the web app exactly as your agent will see it.

### Is there an LLM call on every search?

No. A model is used once, at ingest, to structure and summarize your documents. Retrieval is a search over the index, so it stays fast and predictable.

### Which agents can connect?

Any MCP client that supports streamable HTTP with a bearer key. The docs have setup guides for Claude Code, Claude Desktop, the Anthropic API's MCP connector, the OpenAI Responses API and Agents SDK, Grok (xAI), LangChain and LangGraph, and Qwen and other open-weight models. Connector UIs that require signing in, like Claude.ai, are on the roadmap.

### Can I use it for agent skills?

Yes. Upload one document per skill, or your SKILL.md files as they are: the description in the front matter becomes the skill's line in the map, and the agent loads the whole skill only when a task matches. It works the same with any model that speaks MCP. jitprompt serves the skill's text; scripts bundled in a skill folder aren't run.

### What happens when I change a document?

Edit it in the browser or replace it through the API, and it's re-ingested. The table of contents is built live on every call, so agents see the new version as soon as it's ready. On paid plans the previous versions are kept, so a bad edit is one restore away.

### How is my data isolated?

Every API key is bound to one namespace and can read nothing else. Keys are stored hashed and rate limited, and another organization's pages simply don't exist for you.

## Pages

- [Home](https://www.jitprompt.com/): overview
- [Product](https://www.jitprompt.com/product/): features, walkthrough, plans and FAQ
- [Sign up](https://app.jitprompt.com/ui/signup): create a free account
- [Documentation](https://docs.jitprompt.com/): setup, concepts, API reference — and its own index for models: https://docs.jitprompt.com/llms.txt
- [Blog](https://www.jitprompt.com/blog/): articles and benchmarks

## Blog

- [Prompt stuffing vs RAG vs jitprompt: 23 business rules, 300K tokens](https://www.jitprompt.com/blog/prompt-stuffing-vs-rag-vs-jitprompt/): A benchmark on τ²-bench: the same agent and knowledge base, delivered three ways. At 300K tokens, jitprompt followed 85% of planted business rules (RAG 67%, full prompt 50%) at $0.0086 per conversation, 17× less than the full prompt.

## Legal

- [Data Processing Addendum](https://www.jitprompt.com/dpa/)
- [Privacy Policy](https://www.jitprompt.com/privacy/)
- [Subprocessors](https://www.jitprompt.com/subprocessors/)
- [Terms of Service](https://www.jitprompt.com/terms/)