Cognita (RAG Framework)

Cognita (RAG Framework) MCP Connector for Claude

A+

Manage modular RAG via Cognita — list collections, ingest data sources, and perform AI-driven Q&A directly from any AI agent.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Cognita (TrueFoundry) instance to any AI agent and take full control of your modular RAG workflows through natural conversation.

What you can do

  • Knowledge Collections — List and audit RAG collections to inspect embedding configurations, token lengths, and parser details
  • Data Ingestion — Force sync remote files from SQL, Cloud Storage, or APIs into your vector space to update your knowledge base
  • RAG Queries — Dispatch automated AI questions that query your vector store and synthesize accurate answers from stored context
  • Chunk Auditing — Perform lexical or semantic searches to pull raw document chunks and verify precise text segments
  • Model Registry — Enumerate available LLMs and embedding models registered inside your modular Cognita installation
  • DataSource Management — List all connected data sources to verify which external data is mapped into your AI workflows

How it works

  1. Subscribe to this server
  2. Enter your Cognita Base URL and API Key (if required by your TrueFoundry or self-hosted setup)
  3. Start managing your RAG pipelines from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Engineers — test and debug RAG queries and chunk retrieval logic without writing Python scripts
  • Data Scientists — monitor ingestion pipelines and verify document chunking consistency across collections
  • Product Teams — quickly audit what knowledge is being fed to AI agents during the prototyping phase
  • DevOps Teams — monitor Cognita model registries and ensure that all LLM endpoints are active and reachable
rag-frameworkvector-searchembedding-modelsdata-ingestionai-pipelineknowledge-retrieval

7 tools expose this connector's capabilities to your AI agent.

rag_query

Identify precise active arrays spanning rented Transformation vectors

list_models

Inspect deep internal arrays mitigating specific Picture constraints

list_collections

Identify bounded routing spaces inside the Headless Cognita RAG limit

get_collection

Retrieve explicit Cloud logging tracing explicit Payload IDs

list_data_sources

Perform structural extraction of properties driving active Buckets

ingest_data

Provision a highly-available JSON Payload generating new Resource directories

search_chunks

Enumerate explicitly attached structured rules exporting active Presets

See how to talk to your AI agent using Cognita (RAG Framework).

List all RAG collections in Cognita

I found 3 collections: 'technical-docs', 'legal-kb', and 'customer-support'. Which one would you like to inspect for metadata?

Query collection 'technical-docs' for: 'How do I configure OAuth in our API?'

Based on your technical docs, you need to navigate to the /auth/settings endpoint and register a new client ID. [Detailed answer synthesized from 3 context chunks].

Ingest data from source 'gh-repo-vinkius' into collection 'technical-docs'

Ingestion pipeline triggered! Cognita is now syncing 'gh-repo-vinkius' into the 'technical-docs' collection. I will let you know once the knowledge base is updated.

Yes. The 'rag_query' tool allows you to ask questions in natural language. The agent queries your vector store via Cognita and uses an LLM to synthesize a final answer based explicitly on the retrieved context.

Related Connectors