Mmcp.market

cognee-integrations skill

by topoteretes·topoteretes/cognee·31k stars·Apache-2.0

Use when the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenRouter), changing databases (Postgres, PGVector, Neo4j, Neptune, Turso), S3 storage, or the MCP server for IDE integration.

A100/100content scan

Is the cognee-integrations skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the cognee-integrations skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/topoteretes/cognee.git /tmp/cognee
mkdir -p ~/.claude/skills
cp -r /tmp/cognee/.claude/skills/cognee-integrations ~/.claude/skills/cognee-integrations
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Set up cognee integrations

All integration config is environment variables (.env). The authoritative, always-current list with commented examples is .env.template at the repo root — check it before inventing variable names. Install the matching extra before switching a backend (e.g. pip install cognee[postgres]).

LLM providers

Default is OpenAI (LLMAPIKEY is all you need). To switch, set LLMPROVIDER, LLMMODEL, LLMAPIKEY, and (where relevant) LLMENDPOINT / LLMAPI_VERSION:

  • Azure OpenAI: LLMPROVIDER=azure, LLMMODEL=azure/gpt-4o-mini, endpoint + api version required.
  • Gemini (no extra needed): LLMPROVIDER=gemini, LLMMODEL=gemini/gemini-2.0-flash-exp.
  • Anthropic (cognee[anthropic]): LLM_PROVIDER=anthropic, model e.g. claude-3-5-sonnet-20241022.
  • Ollama, local (cognee[ollama]): LLMPROVIDER=ollama, LLMENDPOINT=http://localhost:11434/v1, and set the embedding block + HUGGINGFACE_TOKENIZER too.
  • Custom / OpenRouter / vLLM: LLM_PROVIDER=custom with the provider's OpenAI-compatible endpoint.
  • AWS Bedrock (cognee[aws]): LLM_PROVIDER=bedrock + AWS credentials/region.

The classic trap: LLM and embeddings are configured independently (EMBEDDINGPROVIDER, EMBEDDINGMODEL, EMBEDDINGENDPOINT, EMBEDDINGAPI_KEY). Configuring only one leaves the other on OpenAI — either keep a valid OpenAI key or configure both.

Databases

(cognee[postgres]; host/port/user/password/name via DB_* vars).

  • Relational (DB_PROVIDER): sqlite (default) or postgres

(cognee[postgres], needs VECTORDBURL), neptuneanalytics (cognee[neptune]), turso (cognee[turso]). Anything else (ChromaDB, Qdrant, Weaviate, Milvus, …) lives in community adapters — install from https://github.com/topoteretes/cognee-community and register with usevectoradapter before use; setting VECTORDB_PROVIDER alone raises "Unsupported vector database provider".

  • Vector (VECTORDBPROVIDER): lancedb (default), pgvector

(cognee[neo4j], bolt URL + credentials), neptune (cognee[neptune]), ladybug-remote, postgres (no raw Cypher / natural-language search).

  • Graph (GRAPHDATABASEPROVIDER): ladybug (default), neo4j

The repo docker-compose.yml ships ready-to-use postgres (pgvector) and neo4j profiles with matching default credentials. From a container, reach host services with DB_HOST=host.docker.internal.

Storage, cache, and the rest

and point DATAROOTDIRECTORY/SYSTEMROOTDIRECTORY at s3:// paths.

  • S3 storage (cognee[aws]): STORAGE_BACKEND=s3 + bucket/credentials,

ONTOLOGYRESOLVER / MATCHINGSTRATEGY.

  • Session cache: CACHE_BACKEND = sqlite (default) | postgres | redis | fs | tapes.
  • Ontologies: ONTOLOGYFILEPATH to an OWL file, resolver/matching via

MCP server (IDE integration)

docker compose --profile mcp up starts the MCP server on port 8001 (Streamable HTTP at http://localhost:8001/mcp), built from cognee-mcp/. Point Cursor / Claude Desktop / Claude Code at it to use cognee memory from the IDE. Configure its DB_* env to match the main service so both see the same data.

After changing providers mid-project

Embeddings from different models are not comparable — after switching the embedding provider or model, reset local state (cognee-cli forget --all or await cognee.forget(everything=True)) and re-ingest with remember().

To drop just the graph and vectors while keeping the ingested files, use await cognee.forget(dataset="myproject", memoryonly=True) — the dataset can then be rebuilt under the new embedding model without re-uploading anything.

More skills from topoteretes/cognee

  • Acognee-cliUse when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.
  • Acognee-communityUse when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, Memgraph, DuckDB, NetworkX, …), data-source connectors (Slack, Gmail, Notion, Confluence, Google Drive), custom tasks/pipelines/retrievers (Exa, ScrapeGraph, codify), Keywords AI observability — or wants to contribute a package to the cognee-community repo.
  • Acognee-dockerUse when the user wants to run cognee with Docker or docker compose — trying it out from the prebuilt image, starting the API server in a container, or bringing up the full stack (UI, MCP, Postgres, Neo4j) with compose profiles.
  • Acognee-installUse when the user wants to install cognee and run their first remember → recall flow with the Python SDK — fresh setup, virtual env, extras selection, or a minimal working example.
  • Acognee-permissionsUse when working with cognee's permission system — understanding or changing how users, roles, and tenants get access to datasets, how ACL grants work, where permissions are enforced in add/cognify/search/delete, and how the grant records surface in the memory-provenance view.
  • Acognee-serverUse when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth posture.
  • Adiff-risk-explainerUse to briefly explain small code diffs.
  • Apr-comment-evaluatorUse to judge whether a PR review comment sounds polite.
  • Askill-feedback-writerUse to identify missing instructions in another skill based on its output.

All agent skills → · MCP servers