mcp-server-mongodb
Provides read-only access to a MongoDB database, enabling collection listing, schema inference from samples, document queries with filters/projections/sorting, read-only aggregations, and counts, with configurable allowlists and operation limits.
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.
mcp-server-mongodb
MCP server that gives LLMs safe, read-only access to MongoDB.
What it does
A Model Context Protocol server over stdio that lets an MCP client (Claude Code, Claude Desktop, ...) explore and query one MongoDB database without being able to change it.
Tool | Purpose |
| Collections the server exposes (respects the allowlist) |
| Inferred field types and presence from a random sample |
| Query documents, hard-capped at 100 |
| Read-only aggregation, hard-capped at 100 results |
| Count matching documents |
It also serves the resource template mongodb://schema/{collection} with the same inferred schema.
Related MCP server: MongoDB Mongoose MCP
Architecture
flowchart LR
Client[MCP client] <-- stdio --> Server[McpServer]
Server --> Tools[tools/*]
Tools --> Guard[validate.ts<br/>operator denylist, allowlist, limit]
Tools --> Infer[schema.ts]
Guard --> Driver[MongoDB driver<br/>maxTimeMS]
Infer --> Driver
Driver --> DB[(MongoDB)]Every tool body runs through respond(), which turns any failure (validation, allowlist, driver error) into a tool result with isError: true so the model can read the message and retry.
Quickstart
npm install
# the server does not load .env: export the variables or set them in your MCP client config
npm run build
MONGODB_URI=mongodb://localhost:27017 MONGODB_DB=sample node dist/index.jsVariable | Required | Meaning |
| yes | Connection string |
| yes | Database to expose |
| no | Comma-separated collections; unset exposes every non- |
| no | Per-operation server-side time limit, default |
Missing required variables abort startup with a message naming the variable. Logs are JSON on stderr only; stdout is the protocol.
Client configuration: examples/claude-code.mcp.json (local Node) and examples/claude-desktop.json (Docker, built with docker build -t mcp-server-mongodb .).
Usage
Example tool calls an LLM might issue (synthetic movies collection):
{ "name": "find", "arguments": { "collection": "movies", "filter": { "year": { "$gte": 2000 } }, "sort": { "year": -1 }, "limit": 5 } }
{ "name": "aggregate", "arguments": { "collection": "movies", "pipeline": [{ "$group": { "_id": "$year", "n": { "$sum": 1 } } }] } }Results are relaxed Extended JSON, and filters accept it too ({"_id": {"$oid": "..."}}, {"$date": "..."}), so ObjectIds and dates round-trip.
Rejected, with an explanatory error: $out / $merge, $function / $accumulator / $where at any depth (also in filters and projections), and $lookup / $graphLookup / $unionWith into collections outside the allowlist.
Design decisions & trade-offs
Denylist plus allowlist, enforced by a deep walk. Validation walks the whole pipeline (including
$facetand$lookupsub-pipelines) rather than inspecting only top-level stages, because the dangerous operators can hide at any depth. The cost is that it can reject a legitimate document whose field happens to be named like an operator.Not a substitute for database permissions. The server is read-only by construction, but the right defence in depth is a MongoDB user with the
readrole only. Use one.Limits are clamped, not rejected.
findlimits above 100 are lowered and aggregations always end in a$limitof at most 100, so a model asking for "everything" gets a useful capped answer. Every operation also carriesmaxTimeMS.Schema inference samples.
describe_collectionuses$sampleand reports presence as a fraction, which is cheap on large collections but can miss rare fields.Tool errors, not protocol errors. Failures return
isError: truewith a short message; collection names outside the allowlist are reported as "not available" without confirming they exist.Shared tool helpers live in
src/tools/shared.tsso each tool file stays a single registration function.
Testing
npm testUnit tests cover pipeline/filter validation, limit enforcement, schema inference and env loading. test/tools.test.ts starts a mongodb-memory-server, seeds 150 synthetic documents and drives the server through the SDK's InMemoryTransport client (limit capping, allowlist, $out and $lookup rejection, schema resource). The first run downloads a mongod binary. CI runs lint, typecheck and tests on every push.
Limitations & next steps
Single database per server instance;
$lookupwith a cross-database{db, coll}reference is rejected.Stdio transport only; no Streamable HTTP or auth layer.
Aggregation stages that expose server internals (for example
$collStats) are not blocked beyond the allowlist; rely on a least-privilege database user.Results are not paginated; the 100-document cap is fixed.
License
MIT
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
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Query 40 databases from Claude, ChatGPT, or Cursor — on any device. Read-only, encrypted, audited.
Astra DB tools for agents: schema, find, vector search, guarded writes, and interactive views.
Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.
Related MCP Servers
- FlicenseNot gradedqualityFmaintenanceProvides read-only access to MongoDB databases for LLMs to inspect collection schemas and execute aggregation pipelines.27-
- AlicenseNot gradedqualityDmaintenanceEnables Claude to interact with MongoDB databases through natural language, supporting queries, aggregations, CRUD operations, and index management with optional Mongoose schema validation.25 npm3MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to query and introspect MongoDB databases through find, aggregate, and schema discovery operations. Supports read-only default mode with optional write capabilities and works with any MCP-compatible client via stdio or HTTP transports.-
- AlicenseBqualityDmaintenanceEnables AI assistants to interact with MongoDB 3.6+ databases, supporting collection listing, document queries, counting, and aggregations through natural language.51MIT