snipara-mcp

snipara-mcp is the lightweight MCP connector for Snipara.

Memory belongs to the project, not the model.

Use it when an MCP client needs a local stdio process that talks to Snipara's hosted project memory and context optimization APIs.

What Is Snipara?

Snipara is project-scoped persistent context for AI-assisted work.

It gives Claude Code, Cursor, Codex, OpenAI Agents, and other MCP-compatible clients a shared memory layer that survives sessions, users, tools, and model switches.

Your agent still uses its own LLM. Snipara gives it the right context.

Why MCP?

MCP is becoming a standard adapter layer for agent tools. snipara-mcp makes Snipara available through that layer without forcing developers into a specific IDE, model, or orchestration framework.

The integration should feel small:

uvx snipara-mcp

The impact is larger: agents can retrieve durable project context instead of starting cold every session.

Architecture

Claude Code       Cursor          Codex          OpenAI Agents
    |               |              |                  |
    +---------------+--------------+------------------+
                    |
             snipara-mcp
                    |
        Hosted Snipara MCP API
                    |
          Shared Project Memory
                    |
        Compact Context for Your LLM

Hosted HTTP Or Stdio?

Use the hosted HTTP endpoint when your MCP client supports streamable HTTP:

{
  "mcpServers": {
    "snipara": {
      "type": "http",
      "url": "https://api.snipara.com/mcp/your-project-id-or-slug",
      "headers": {
        "Authorization": "Bearer rlm_your_api_key"
      }
    }
  }
}

Use snipara-mcp when your client expects a local stdio command:

{
  "mcpServers": {
    "snipara": {
      "command": "uvx",
      "args": ["snipara-mcp"],
      "env": {
        "SNIPARA_API_KEY": "rlm_your_api_key",
        "SNIPARA_PROJECT_ID": "your-project-id-or-slug"
      }
    }
  }
}

Install

No local install:

uvx snipara-mcp

Python package:

pip install snipara-mcp

With RLM Runtime helper integration:

pip install "snipara-mcp[rlm]"

Quickstart

Sign in through the browser:

pip install snipara-mcp
snipara login

Initialize a project:

snipara init

The initializer detects common project files, writes MCP configuration, and can upload local project docs when you are authenticated.

Useful options:

snipara init --slug my-project
snipara init --dry-run
snipara init --no-upload
snipara init --skip-test

Claude Code

claude mcp add snipara -- uvx snipara-mcp

Then export credentials in your shell:

export SNIPARA_API_KEY="rlm_your_api_key"
export SNIPARA_PROJECT_ID="your-project-id-or-slug"

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "snipara": {
      "command": "uvx",
      "args": ["snipara-mcp"],
      "env": {
        "SNIPARA_API_KEY": "rlm_your_api_key",
        "SNIPARA_PROJECT_ID": "your-project-id-or-slug"
      }
    }
  }
}

Environment

OAuth tokens created by snipara login are stored in ~/.snipara/tokens.json. If a project id or slug is set, the connector selects the matching token and does not silently fall back to another project.

What You Get

The connector exposes the same MCP contract as the hosted backend. The packaged tool surface is generated from the server source of truth.

Common tool groups:

• retrieval: rlm_context_query, rlm_search, rlm_get_chunk, rlm_load_document

• durable memory: rlm_recall, rlm_remember, rlm_memory_compact

• shared context: rlm_shared_context, collection and template tools

• document upload: rlm_upload_document, rlm_sync_documents

• project setup: client, project, and business-context workspace tools

• operations: rlm_settings, rlm_index_health, rlm_reindex

• code graph: rlm_code_* tools when code indexes are available

• coordination: swarm, hierarchical task, and state tools when enabled

Tool availability can vary by plan, hosted deployment, and project index state.

CLI Commands

Legacy aliases such as snipara-init, snipara-mcp-login, snipara-mcp-logout, and snipara-mcp-status are still supported.

Relationship To Other Repos

snipara-mcp is intentionally thin. It should be easy to install, easy to audit, and boring to operate. The heavy lifting stays in Snipara's hosted context and memory engine.

Development

pip install -e ".[dev]"
pytest
ruff check .

The source of truth for the generated tool contract lives in the Snipara server. When backend tools change, regenerate the packaged contract before publishing this package.

License

MIT. See LICENSE.