blob-storage
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Blob Storage Service
A lightweight MCP data broker that stores large binary payloads under a UUID, enabling MCP clients and agents to exchange massive results without flooding the LLM context window.
Architecture
MCP Client / LLM Agent
│
│ tool call (large result)
▼
MCP Server ──store_blob──▶ Blob Storage Service ──▶ SQLite + local files
│ │
│ returns UUID │ retrieve_blob(uuid)
◀──────────────────────────────┘The agent only ever sees a UUID token — not the raw bytes.
Related MCP server: Librarian
Project Structure
src/blob_storage/
├── __init__.py # package metadata
├── config.py # pydantic-settings (env / .env)
├── models.py # SQLAlchemy ORM + Pydantic schemas
├── database.py # async engine, session factory, init_db()
├── storage.py # StorageBackend ABC + LocalFileBackend
├── service.py # BlobService (orchestration)
├── api.py # FastAPI REST API
└── mcp_server.py # MCP server (HTTP Streamable, /mcp)
tests/
├── conftest.py # shared fixtures
├── test_api.py # API integration tests
└── test_service.py # service unit testsQuickstart
Install dependencies
uv syncStart the REST API
uv run blob-api # defaults from config / .env
uv run blob-api --host 0.0.0.0 --port 9000 # override at runtimeInteractive docs available at http://<host>:<port>/docs.
Start the MCP server
uv run blob-mcp # defaults: 0.0.0.0:8001
uv run blob-mcp --host 0.0.0.0 --port 9001The MCP endpoint is served at http://<host>:<port>/mcp.
Configuration
Settings are read from environment variables or a .env file in the project root.
Variable | Default | Description |
|
| Directory for blob files |
|
| SQLAlchemy async DB URL |
|
| Default TTL — 90 days. Use |
|
| Max upload size (500 MB) |
|
| REST API bind address |
|
| REST API port |
|
| MCP server bind address |
|
| MCP server port |
|
| REST API URL used internally by the MCP server |
|
| How often the TTL cleanup job runs |
CLI flags (
--host,--port) take precedence over config/env for the respective server.
REST API Reference
Method | Path | Description |
|
| Liveness check |
|
| Store a blob |
|
| Download a blob |
|
| Metadata only (no payload) |
|
| Delete a blob |
Store a blob
Pass metadata as custom request headers:
Header | Default | Description |
|
| MIME type of the payload |
| config default | Override TTL; |
| — | Free-form source identifier |
| — | JSON object for arbitrary labels |
curl -X POST http://localhost:8000/blobs \
-H "Content-Type: application/octet-stream" \
-H "X-Mime-Type: application/json" \
-H "X-Origin: my-mcp-server" \
--data-binary '{"key": "value"}'Response:
{
"uuid": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"expires_at": "2026-05-30T16:42:07Z",
"size_bytes": 16
}MCP Integration
The MCP server uses the Streamable HTTP transport. Configure your MCP host to connect over HTTP rather than spawning a subprocess:
{
"mcpServers": {
"blob-storage": {
"type": "http",
"url": "http://127.0.0.1:8001/mcp"
}
}
}Available tools
Tool | Input | Output |
|
|
|
|
|
|
|
| metadata JSON |
|
|
|
All binary data is base64-encoded in MCP tool calls (MCP messages are JSON/text).
Running Tests
uv run pytest tests/ -vExtending the Storage Backend
To use S3 or MinIO in production, implement the StorageBackend abstract class in storage.py:
from blob_storage.storage import StorageBackend
class S3Backend(StorageBackend):
async def store(self, blob_uuid: str, data: bytes) -> None: ...
async def retrieve(self, blob_uuid: str) -> bytes: ...
async def delete(self, blob_uuid: str) -> None: ...Then inject it into BlobService and the _backend singleton in api.py.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent file storage for AI agents. Save files over MCP, get a link a human can open.
Persistent file storage for AI agents via MCP and curl. Upload, download, and version files.
Hosted memory for AI agents over MCP. One memory shared by all your agents.
Cross-tool persistent memory and context for AI assistants over MCP.
Related MCP Servers
- AlicenseAqualityDmaintenanceStore and retrieve data objects for free. Temporary cloud storage for agents. Two hour expiry. Works with any format and flow. Example use cases include: * Manage large datasets across different sessions * Generate shareable links for intermediate results * Streamline complex workflows by bridging information between multiple contexts274 npm1MIT
- AlicenseNot gradedqualityCmaintenanceProvides AI agents with persistent knowledge storage, enabling them to store, search, and retrieve text, documents, and files using semantic and keyword search via MCP tools.34Apache 2.0
- AlicenseNot gradedqualityBmaintenanceLightweight object storage with S3, HTTP, and MCP interfaces, enabling AI agents to store and retrieve files via structured tool definitions.5Do What The F*ck You Want To Public
- AlicenseNot gradedqualityBmaintenanceA local, agent-to-agent artifact exchange for LLM workflows. Enables MCP-capable tools like Claude, Codex, and Gemini to publish, list, read, update, and continue from artifacts without copying content through chat.347 npmMIT