search_content
Semantic search across your approved content library. Filter by tag.
LABSCO SUMMARY
Read-only with citations is exactly right for answer libraries, where the risk is a confident wrong answer.
RFP work fails when someone pastes an approved-sounding answer that was never approved. Returning a trust score and the source alongside each result makes that checkable, and the scopes make it structurally impossible for the agent to write a new answer into the library. list_content_usage is the underrated one: knowing an answer has been reused across twelve projects tells you more about whether to trust it than any score.
What it is
AutoRFP's endpoint, published as a read-only release — the write tools are stated as future work. There is one endpoint per region: US, EU and AU.
What you get
- search_content — semantic search across your approved content library, filtered by tag
- list_content and list_content_usage — enumerate the library, and reverse-look-up which projects reused a piece
- list_projects and get_project — RFPs, DDQs and questionnaires with requirement status counts
- list_requirements — the questions and answers inside a project, filtered by status, tag, editor or whether an answer exists
- list_tags — the organisation's tag vocabulary, so every other call can be scoped correctly
Requirements
Per-user OAuth with three read scopes: tags:read, projects:read and content:read. Responses carry a trust score and source citation metadata.
Setup effort
Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen
USE CASES
01
Finding the approved answer to a question
Scope by tag, search the library semantically, and read the trust score and source before using it.
02
Seeing what is still unanswered
List the project's requirements filtered by whether an answer exists.
03
Checking whether an answer is actually in use
Reverse-look-up which projects and requirements have reused a piece of content.
04
Keeping data in region
Point at the EU endpoint rather than the US one when that matters.
7 tools
Listed in project docs. Your client may show a different list.
list_content
Enumerate your library by tag, file type, or date range.
list_content_usage
Reverse-lookup which projects and requirements have reused a piece of content (auto-generated vs manually inserted).
list_projects
List your RFP, DDQ, and questionnaire projects. Filter by status, due date, or tag.
get_project
Pull full project details: header, requirement status counts, applied tags.
list_requirements
Paginated questions and answers within a project. Filter by status, tags, lastUpdatedBy, or whether an answer exists.
list_tags
Discover your organisation's full tag vocabulary so the agent can scope every other call correctly.
BEFORE YOU INSTALL
What to know first
Tools you get
7 tools named in the project's documentation.
Requires
- an MCP client that can reach a remote endpoint
- OAuth per user (scopes tags:read, projects:read, content:read)
INSTALLATION
Connect your client
Add the endpoint to your client, then approve the OAuth consent screen.
Server setup
ENDPOINT URL
https://api.us.autorfp.ai/mcpRequirements
- OAuth per user (scopes tags:read, projects:read, content:read)
MCP Clients
Any MCP client
Pick the address for the region your AutoRFP.ai workspace is in — https://api.us.autorfp.ai/mcp (US), https://api.eu.autorfp.ai/mcp (EU) or https://api.autorfp.ai/mcp (AU)
Add it to your MCP client as a remote server, then approve the AutoRFP.ai OAuth consent screen when the client opens it
