Developers

MCP Server

Model Context Protocol integration for agent runtimes. Give your AI agents native tool access to search, fetch documents, and monitor changes.


What is MCP?

Open standard for agent tool integration

The Model Context Protocol (MCP) is an open standard for connecting AI models to external tools and data sources. Instead of calling REST APIs directly, agents discover and invoke tools through a standardized interface. The RLVNCE MCP server exposes corpus operations as native agent tools.


Available tools

Corpus operations exposed as agent tools

search

Search a corpus with queries, filters, and ranking controls

list_corpora

List available corpora and their metadata

get_document

Fetch a specific document by ID with full content

list_changes

Get document changes since a timestamp

list_sources

List sources in a corpus with health status

get_corpus

Get corpus details, configuration, and metrics

sample_documents

Sample random documents for exploration

trigger_crawl

Trigger a crawl for a corpus

add_sources

Add new sources to a corpus


Integration

Connect with your agent runtime

Claude

Add the RLVNCE MCP server to your Claude configuration. Claude discovers available tools and can search your corpora, fetch documents, and monitor changes natively.

Other runtimes

Any MCP-compatible agent runtime can connect to the RLVNCE server. The protocol is open - no vendor lock-in.

Give your agents native search

Connect your agent runtime to RLVNCE via MCP.

Get started