canonical: https://jentic.com/apis/autorfp.ai/autorfp # AutoRFP.ai Agent API The AutoRFP.ai Agent API provides discovery and read access to an AutoRFP.ai workspace for AI agents. Public discovery endpoints return agent resources, site identity, resource listings, and the OpenAPI and Swagger documents without credentials. An authenticated Model Context Protocol endpoint, scoped by OAuth, returns the workspace's tag vocabulary, projects and their requirements, and approved answer content and its usage, always limited to what the authorized user can see. ## For AI agents Discover an AutoRFP.ai workspace and read its projects, requirements, and approved RFP content through an OAuth-scoped, read-only endpoint. Public discovery endpoints need no credential. ## Scope Does not draft, submit, or edit proposal responses, and does not place or price orders. Use for discovering AutoRFP.ai resources and reading RFP projects, requirements, and approved content only. ## Capabilities - Discover AutoRFP.ai agent resources, site identity, and public resource listings - Read the OpenAPI and Swagger documents for the API - Discover the Model Context Protocol server and its capability catalogs - Read a workspace's projects and their requirements through the authenticated endpoint - Search and read approved RFP answer content and its usage, scoped to the authorized user ## Use cases ### AI Agent RFP Integration via Jentic An agent that drafts or researches RFP responses can reach an AutoRFP.ai workspace through Jentic without handling the OAuth dance or the discovery endpoints. The agent searches by intent, authorizes once, and reads the workspace's projects, requirements, and approved content as structured data. This fits proposal-assistant agents that need grounded, approved answer material rather than invented text. Example prompt: Search Jentic for 'search approved content', authorize with OAuth, and read the matching approved answers for an RFP question ### RFP Content Retrieval Pull approved answer content from a workspace to ground an RFP response. The authenticated endpoint, with the content read scope, searches and returns approved content and its usage, so a proposal agent reuses vetted material instead of generating unverified claims. Access is limited to what the authorized user can see. Example prompt: Call POST /mcp with a content read request to search approved RFP content for a topic ### Workspace and Resource Discovery Discover what an AutoRFP.ai workspace exposes before calling it. The public endpoints return agent resources, site identity, resource listings, and the machine-readable OpenAPI document, so an agent can orient itself and register without any credential. Example prompt: Call GET `/api/v1/resources.json` to list the public API resources, then GET `/api/v1/site.json` for the site identity ### Requirement Reading for Proposals Read a project's requirements so an agent can structure a response around them. With the projects read scope, the authenticated endpoint returns the workspace's projects and the requirements inside them, giving the agent the questions to answer before it retrieves content. Example prompt: Call POST /mcp to read a project's requirements before drafting a response ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | `/api/agent-resources.json` | List AutoRFP.ai agent resources | | GET | `/api/v1/site.json` | Read public site identity | | GET | `/api/v1/resources.json` | List public API resources | | GET | `/openapi.json` | Download the OpenAPI document | | GET | `/.well-known/mcp.json` | Discover the Model Context Protocol server | | GET | `/.well-known/agent-skills/index.json` | Read the agent-skills discovery index | | GET | `/auth.md` | Read agent registration instructions | | POST | `/mcp` | Send an authenticated Model Context Protocol request | ## Key resources - **Discovery** — Agent resources, site identity, resource listings, and spec documents - **Well-known catalogs** — Model Context Protocol, API catalog, and agent-skills discovery - **Projects** — Workspace projects and their requirements, read-only via the authenticated endpoint - **Content** — Approved answer content and its usage, scoped to the authorized user ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 71 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 100 / 100 - Developer Experience & Jentic Compatibility: 59 / 100 - AI-Readiness & Agent Experience: 52 / 100 - Agent Usability: 94 / 100 - Security: 90 / 100 - AI Discoverability: 78 / 100 - **View full report:** https://jentic.com/apis/autorfp.ai/autorfp/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the AutoRFP.ai API by hand means registering an OAuth client with PKCE, requesting the read scopes you need, and calling the discovery endpoints before the content gateway. Through Jentic you install once, import AutoRFP.ai from the API Directory, store the OAuth credential once, and your agent calls it. - **Permission scoping:** AutoRFP.ai gates its read access behind OAuth scopes for tags, projects, and content, so a rule can grant your agent only the scopes and operations you choose. You decide which reads it may perform, so it can search content without reaching anything the scopes do not cover. - **Credential handling:** Your AutoRFP.ai OAuth credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'read a project's requirements' or 'search approved content', and Jentic returns the matching AutoRFP.ai operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Notion API** — General knowledge workspace for storing and reading content - **Showpad Sales Enablement API** — Sales enablement content library and assets - **Coda API** — Docs and tables for collaborative content ## FAQ ### Is there an AutoRFP.ai MCP server? Yes, AutoRFP.ai publishes a read-only Model Context Protocol server, and you can also connect it directly through Jentic from the API Directory: import it, authorize once with OAuth, and your agent calls the discovery and content operations without loading another server's tool definitions into its context. ### Can I limit what my agent is allowed to do with the AutoRFP.ai API? Yes. The API is read-only and gated by OAuth scopes, so you grant your agent just the scopes it needs, such as reading projects and content, and it can search and read while anything outside those scopes is refused. Every call is logged by your self-hosted instance. ### What authentication does the AutoRFP.ai API use? The authenticated endpoint uses OAuth 2.0 authorization code with PKCE and read scopes for tags, projects, and content, per its OpenAPI spec; the discovery endpoints are public and need no credential. Through Jentic the OAuth credential is stored encrypted by your own Jentic One instance and injected at call time. ### Can I read RFP project requirements with the AutoRFP.ai API? Yes. With the projects read scope, the authenticated endpoint returns a workspace's projects and their requirements, and the content read scope returns approved answer content and its usage. Access stays limited to what the authorized user can see. ### What are the rate limits for the AutoRFP.ai API? The OpenAPI spec does not specify rate limits. Check the vendor's documentation at https://autorfp.ai for current limits. ### How do I read a project's requirements with the AutoRFP.ai API through Jentic? Search Jentic for 'read a project's requirements' and it returns the AutoRFP.ai operation with its input schema; authorize once with OAuth and the agent reads the requirements as structured data. To run it on your own infrastructure, install Jentic One from its GitHub repo.