documentdb MCP server
Commit Nov 13, 2026Enables AI clients to perform CRUD operations, manage collections, and ingest data into knowledge graphs using a DocumentDB backend.
Also known as Knuckles-Team/documentdb-mcp
- Stars
- 2
- Tools
- 31
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 13, 2026
- License
- MIT
What is documentdb MCP?
documentdb enables AI clients to perform CRUD operations, manage collections, and ingest data into knowledge graphs using a DocumentDB backend. It exposes 31 tools, such as documentdb_ingest_catalog, documentdb_ingest_documents, documentdb_aggregate.
Summary generated from the project's README
About documentdb MCP server
Managing document databases through AI clients is what this server enables for developers and data engineers. It provides a bridge between large language models and a DocumentDB backend, allowing for standard CRUD operations, collection management, and database administration. Users can interact with their data using tools like documentdb_find, documentdb_insert_one, or documentdb_aggregate to perform complex queries and data manipulation.
This server supports both local stdio transport for IDEs like Claude Desktop or Cursor and remote streamable-http transport for production environments. It requires connection details such as MONGODB_URI, MONGODB_HOST, and MONGODB_PORT to function. To prevent context window issues, it features dynamic tool selection, allowing operators to toggle specific tool modules like KGTOOL for knowledge graph ingestion or CRUD_CLIENTTOOL for standard operations via environment variables or CLI arguments.
Beyond simple data retrieval, the server can ingest a DocumentDB catalog into an epistemic-graph as typed nodes using documentdb_ingest_catalog. It also includes enterprise features like OpenTelemetry exports and Langfuse tracing for monitoring performance and execution context.
What you can do with it
- 1Ingest data into knowledge graphsTransform stored documents from a collection into typed nodes within an epistemic-graph.
- 2Perform database administration tasksManage the structure of your database by creating or dropping collections and databases.
- 3Execute complex data analysisRun aggregation pipelines to analyze document data directly through an AI interface.
- 4Optimize LLM context usageRestrict the number of available tools to prevent overwhelming the model's context window.
Written from the project's README. Every use case is checked against a quote from it.
documentdb MCP tools 31
Detected from the READMEdocumentdb_ingest_catalogdocumentdb_ingest_documentsdocumentdb_aggregatedocumentdb_binary_versiondocumentdb_count_documentsdocumentdb_create_collectiondocumentdb_create_databasedocumentdb_create_userdocumentdb_delete_manydocumentdb_delete_onedocumentdb_distinctdocumentdb_drop_collection
Show all 31 toolsShow fewer tools
documentdb_drop_databasedocumentdb_drop_userdocumentdb_finddocumentdb_find_onedocumentdb_find_one_and_deletedocumentdb_find_one_and_replacedocumentdb_find_one_and_updatedocumentdb_insert_manydocumentdb_insert_onedocumentdb_list_collectionsdocumentdb_list_databasesdocumentdb_rename_collectiondocumentdb_replace_onedocumentdb_run_commanddocumentdb_update_manydocumentdb_update_onedocumentdb_update_userdocumentdb_users_infox-mcp-enabled
Configuration
MCP_TOOL_MODEMONGODB_HOSTMONGODB_PORTMONGODB_URI
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableknuckles-team/documentdb-mcp is public and reachablegithub.com/knuckles-team/documentdb-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/knuckles-team/documentdb-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model31 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubDocumentdb Mcp
CLI or API | MCP
Documentation — Installation, deployment, usage across the API, CLI, MCP, and agent interfaces, and guidance for provisioning the DocumentDB backing service are maintained in the official documentation.
Overview
Key Features
- Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
- Enterprise-Grade Security: Complete support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
- Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.
CLI or API
Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.
MCP
This server use dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.
Available MCP Tools
Auto-generated — do not edit (synced by the mcp-readme-table pre-commit hook).
Knowledge-graph tools
| Tool | Toggle | Purpose |
|---|---|---|
documentdb_ingest_catalog |
KGTOOL |
Natively ingest the DocumentDB catalog into epistemic-graph as typed nodes. |
documentdb_ingest_documents |
KGTOOL |
Natively ingest stored documents from a collection as :Document nodes. |
Operation tools (one per client method)
| MCP Tool | Toggle Env Var | Description |
|---|---|---|
documentdb_aggregate |
ANALYSIS_CLIENTTOOL |
Invoke the aggregate operation. |
documentdb_binary_version |
SYSTEM_CLIENTTOOL |
Invoke the binary_version operation. |
documentdb_count_documents |
CRUD_CLIENTTOOL |
Invoke the count_documents operation. |
documentdb_create_collection |
SYSTEM_CLIENTTOOL |
Invoke the create_collection operation. |
documentdb_create_database |
SYSTEM_CLIENTTOOL |
Invoke the create_database operation. |
documentdb_create_user |
USERS_CLIENTTOOL |
Invoke the create_user operation. |
documentdb_delete_many |
CRUD_CLIENTTOOL |
Invoke the delete_many operation. |
documentdb_delete_one |
CRUD_CLIENTTOOL |
Invoke the delete_one operation. |
documentdb_distinct |
ANALYSIS_CLIENTTOOL |
Invoke the distinct operation. |
documentdb_drop_collection |
SYSTEM_CLIENTTOOL |
Invoke the drop_collection operation. |
documentdb_drop_database |
SYSTEM_CLIENTTOOL |
Invoke the drop_database operation. |
documentdb_drop_user |
USERS_CLIENTTOOL |
Invoke the drop_user operation. |
documentdb_find |
CRUD_CLIENTTOOL |
Invoke the find operation. |
documentdb_find_one |
CRUD_CLIENTTOOL |
Invoke the find_one operation. |
documentdb_find_one_and_delete |
CRUD_CLIENTTOOL |
Invoke the find_one_and_delete operation. |
documentdb_find_one_and_replace |
CRUD_CLIENTTOOL |
Invoke the find_one_and_replace operation. |
documentdb_find_one_and_update |
CRUD_CLIENTTOOL |
Invoke the find_one_and_update operation. |
documentdb_insert_many |
CRUD_CLIENTTOOL |
Invoke the insert_many operation. |
documentdb_insert_one |
CRUD_CLIENTTOOL |
Invoke the insert_one operation. |
documentdb_list_collections |
SYSTEM_CLIENTTOOL |
Invoke the list_collections operation. |
documentdb_list_databases |
SYSTEM_CLIENTTOOL |
Invoke the list_databases operation. |
documentdb_rename_collection |
SYSTEM_CLIENTTOOL |
Invoke the rename_collection operation. |
documentdb_replace_one |
CRUD_CLIENTTOOL |
Invoke the replace_one operation. |
documentdb_run_command |
SYSTEM_CLIENTTOOL |
Invoke the run_command operation. |
documentdb_update_many |
CRUD_CLIENTTOOL |
Invoke the update_many operation. |
documentdb_update_one |
CRUD_CLIENTTOOL |
Invoke the update_one operation. |
documentdb_update_user |
USERS_CLIENTTOOL |
Invoke the update_user operation. |
documentdb_users_info |
USERS_CLIENTTOOL |
Invoke the users_info operation. |
28 operation tool(s) and 2 knowledge-graph tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (intent default — the six verb-tools, granular set loaded on demand · condensed action-routed · verbose 1:1 · both). Auto-generated — do not edit.
Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/usage.md.
Dynamic Tool Selection & Visibility
This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows the operator to restrict the set of exposed tools to prevent blowing up the LLM's context window.
The operator can configure tool filtering via multiple input channels:
- CLI Arguments: Pass
--toolsor--toolsets(or their disabled counterparts--disabled-toolsand--disabled-toolsets) during startup. - Environment Variables: Define standard environment variables:
MCP_ENABLED_TOOLS/MCP_DISABLED_TOOLSMCP_ENABLED_TAGS/MCP_DISABLED_TAGS
- HTTP SSE Request Headers: Pass custom headers during transport initialization:
x-mcp-enabled-tools/x-mcp-disabled-toolsx-mcp-enabled-tags/x-mcp-disabled-tags
- HTTP SSE Request Query Parameters: Append query parameters directly to the operator's transport connection URL:
?tools=tool1,tool2?tags=tag1
When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.
MCP Configuration Examples
Install the connector-focused
[mcp]extra. Examples usedocumentdb-mcp[mcp]to add FastMCP / FastAPI throughscion-sdk; the required Scion SDK core still carriesepistemic-graph[full]. The[agent-runtime]extra additionally enables model orchestration.
stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)
{
"mcpServers": {
"documentdb-mcp": {
"command": "uvx",
"args": [
"--from",
"documentdb-mcp[mcp]",
"documentdb-mcp"
],
"env": {
"MCP_TOOL_MODE": "intent",
"ANALYSISTOOL": "True",
"COLLECTIONSTOOL": "True",
"CRUDTOOL": "True",
"KGTOOL": "True",
"MONGODB_HOST": "localhost",
"MONGODB_PORT": "27017",
"MONGODB_URI": "mongodb://localhost:27017/",
"SYSTEMTOOL": "True",
"USERSTOOL": "True"
}
}
}
}
Runtime references require an alias-aware launcher such as Arbora. Other launchers must omit those entries and inject the resolved values through their own runtime secret boundary.
Streamable-HTTP Transport (networked / production)
{
"mcpServers": {
"documentdb-mcp": {
"command": "uvx",
"args": [
"--from",
"documentdb-mcp[mcp]",
"documentdb-mcp",
"--transport",
"streamable-http",
"--port",
"8000"
],
"env": {
"TRANSPORT": "streamable-http",
"HOST": "127.0.0.1",
"PORT": "8000",
"MCP_TOOL_MODE": "intent",
"ANALYSISTOOL": "True",
"COLLECTIONSTOOL": "True",
"CRUDTOOL": "True",
"KGTOOL": "True",
"MONGODB_HOST": "localhost",
"MONGODB_PORT": "27017",
"MONGODB_URI": "mongodb://localhost:27017/",
"SYSTEMTOOL": "True",
"USERSTOOL": "True"
}
}
}
}
Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:
{
"mcpServers": {
"documentdb-mcp": {
"url": "http://localhost:8000/documentdb-mcp/mcp"
}
}
}
Run a reviewed container image as a least-privilege stdio child (no listener or published port):
docker run -i --rm \
--read-only \
--cap-drop=ALL \
--security-opt=no-new-privileges \
--pids-limit=256 \
--tmpfs /tmp:rw,noexec,nosuid,nodev,size=64m \
-e TRANSPORT=stdio \
-e MCP_TOOL_MODE=intent \
-e ANALYSISTOOL=True \
-e COLLECTIONSTOOL=True \
-e CRUDTOOL=True \
-e KGTOOL=True \
-e MONGODB_HOST=localhost \
-e MONGODB_PORT=27017 \
-e MONGODB_URI=mongodb://localhost:27017/ \
-e SYSTEMTOOL=True \
-e USERSTOOL=True \
registry.example.invalid/documentdb-mcp@sha256:<digest> documentdb-mcp
For containerized network HTTP, supply an authenticated TLS ingress (or
direct server TLS), exact MCP_ALLOWED_HOSTS, and an exact trusted-proxy
CIDR policy through the operator-owned deployment profile. The generator
does not emit an unauthenticated non-loopback listener.
Auto-generated from the code-read env surface (MCP_TOOL_MODE + package vars) — do not edit.
Additional Deployment Options
documentdb-mcp can run as a local stdio process or container, or behind a remote
network boundary. The
Deployment guide carries
the detailed transport contract.
- Local container — launch a reviewed immutable image as a least-privilege stdio child with no listener or published port.
- Remote URL — connect through an operator-supplied authenticated HTTPS
ingress. Keep its URL, outbound identity references, trust profile, and exact
MCP_ALLOWED_HOSTSinAgentConfig.
Agent
Set credentials
export MONGODB_URI="mongodb://localhost:27017/" export MONGODB_HOST="localhost" export MONGODB_PORT="27017"
Connector-focused MCP server (includes the shared graph engine)
uv pip install "documentdb-mcp[mcp]"
Everything (development)
uv pip install "documentdb-mcp[all]" # or: python -m pip install "documentdb-mcp[all]"
### Container images (`:mcp`)
One multi-stage `docker/Dockerfile` builds the MCP-only image (`--target mcp`):
| Image tag | Build target | Contents | Entrypoint |
|-----------|--------------|----------|------------|
| `example/documentdb-mcp:mcp` | `--target mcp` | `documentdb-mcp[mcp]` — **connector-focused**, includes `epistemic-graph[full]`; no model-orchestration stack | `documentdb-mcp` |
```bash
docker build --target mcp -t example/documentdb-mcp:mcp docker/ # connector-focused MCP server
agent (immutable agent digest) with a co-located :mcp sidecar.
Knowledge-graph database (epistemic-graph)
Scion SDK core dependency (epistemic-graph[full]). The [mcp] extra keeps
deployments can use the bundled engine. For production or shared state, run
epistemic-graph as a dedicated database service and configure the runtime to use it.
Deployment recipes (single-node + Raft HA), connection configuration, and architecture
diagrams are documented in the
epistemic-graph deployment guide.
This graph service is distinct from the DocumentDB backing store used by the MCP tools; see
the connection variables above.
Documentation
The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.
| Page | Contents |
|---|---|
| Installation | pip, source, extras, prebuilt Docker image |
| Deployment | run the MCP server and agent, Compose, Caddy + Technitium, env config |
| Usage | the MCP tools, the DocumentDBApi client, the CLI |
| Backing Platform | deploy DocumentDB with Docker |
| Overview | ecosystem role, tool modules, configuration |
| Concepts | concept registry (CONCEPT:DOCDB-*) |
Repository Owners
Contribute
Contributions are welcome! Please ensure code quality by running local checks before submitting pull requests:
- Format code using
ruff format . - Lint code using
ruff check . - Validate type-safety with
mypy . - Run test suites using
pytest
Deploy with scion-sdk-deployment
Provision this package with the consolidated scion-sdk-deployment
workflow. It selects an installed-package, editable-source, or immutable-container
path; records only runtime secret and TLS-profile references in AgentConfig; and
runs doctor, registration, policy, observability, and rollback gates. Ask your agent
to "deploy documentdb-mcp with scion-sdk-deployment".
| Install mode | Command |
|---|---|
| Installed package | uv tool install "documentdb-mcp[mcp]", then run documentdb-mcp |
| Immutable container | deploy registry.example.invalid/documentdb-mcp@sha256:<digest> through the operator-selected orchestrator |
The repository embeds no deployment profile, credential value, certificate path, or
environment-specific endpoint. Supply those at runtime through AgentConfig and the
configured secret provider.
Governed capability contract
This package ships a compact canonical skill surface with specialist procedures
kept as referenced workflows. The current MCP tools, skill metadata,
connector_manifest.yml, ontology, mappings, shapes, fixtures, migrations,
tool-schema fingerprints, and certification metadata form one versioned
capability contract. Validate them together; do not rely on stale tool names or
historical per-task skill wrappers.
Runtime endpoints, credentials, certificate trust, tenant identity, retention, and observability policy are deployment inputs and are never packaged values. See Configuration, trust, and privacy before enabling a network transport, connector ingestion, Arbora delegation, or trace export.
documentdb MCP questions
What tools does documentdb MCP provide?
It exposes 31 tools, including documentdb_ingest_catalog, documentdb_ingest_documents, documentdb_aggregate, documentdb_binary_version, documentdb_count_documents.
How can I limit the number of tools exposed to the LLM?
You can use dynamic tool selection via CLI arguments, environment variables, or HTTP headers to filter tools and prevent context window bloat.
What kind of security features does the server support?
The server provides enterprise-grade security including Eunomia policies, OIDC token delegation, and granular execution context tracking.
Does the server support observability?
Yes, it includes native OpenTelemetry exports and Langfuse tracing out of the box.