Skip to main content
Glama
Sign In
S2 StreamStore MCP Server

S2 StreamStore MCP Server

by s2-streamstore
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

S2 StreamStore MCP Server

An MCP server for S2 StreamStore built with Concierge progressive tool disclosure.

Instead of exposing all S2 API tools at once, the server guides AI agents through a natural workflow:

account → basin → stream

At each stage, only the relevant tools are visible.

Stages

Stage

Tools

Description

account

list_basins, create_basin, select_basin, list_access_tokens, issue_access_token, revoke_access_token, account_metrics

Manage basins and access tokens

basin

get_basin_config, reconfigure_basin, delete_basin, list_streams, create_stream, select_stream, basin_metrics, go_back_to_account

Manage streams within a basin

stream

get_stream_config, reconfigure_stream, delete_stream, append_records, read_records, check_tail, stream_metrics, go_back_to_basin

Read/write records and manage stream config

Related MCP server: Omega MCP Server

Setup

pip install -e .

Configuration

Set your S2 access token as an environment variable:

export S2_ACCESS_TOKEN="your-token-here"

Run

stdio (for Cursor, Claude Desktop, etc.):

python main.py

MCP Client Configuration

Add to your MCP client config (e.g. ~/.cursor/mcp.json):

{
  "mcpServers": {
    "s2": {
      "command": "python",
      "args": ["/path/to/mcp/main.py"],
      "env": {
        "S2_ACCESS_TOKEN": "your-token-here"
      }
    }
  }
}

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Resources

Related MCP Connectors

Related MCP Servers

  • Streamline MCP

    RosTeHeA
    A
    license
    B
    quality
    B
    maintenance
    Enables AI assistants to access and manage Streamline tasks, notes, tags, and workspaces via a Supabase-powered backend. It supports full CRUD operations, allowing users to search, create, update, and organize their productivity data through natural language.
    17
    11 npm
    MIT

  • Gumloop MCP Server

    thenavidm
    A
    license
    B
    quality
    B
    maintenance
    Enables AI agents to inspect saved flows and their input schemas, start and monitor runs, and manage agents, sessions, skills, Brain knowledge, artifacts and account administration through 92 tools. Operations are confirmation-gated and use explicitly selected private credential profiles for account and team access.
    92
    45 npm
    1
    AGPL 3.0

  • @atengk/mcp-server-s3

    atengk
    A
    license
    C
    quality
    A
    maintenance
    Enables LLM and AI agent clients to manage S3-compatible object storage such as MinIO, AWS S3, Aliyun OSS, Cloudflare R2, and Tencent COS through the Model Context Protocol. It provides 19 production-grade tools covering bucket lifecycle, object browsing, search, text and byte-range reads, streaming uploads/downloads, presigned URLs, moves, batch deletion, and tag management, protected by read-only, sandbox, prefix-deletion, and content-truncation guards.
    21
    31 npm
    MIT