# Documentdb Mcp

> DocumentDB A2A + MCP Server

- **Type:** MCP server
- **Install:** `agentstack add mcp-knuckles-team-documentdb-mcp`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Knuckles-Team](https://agentstack.voostack.com/s/knuckles-team)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Knuckles-Team](https://github.com/Knuckles-Team)
- **Source:** https://github.com/Knuckles-Team/documentdb-mcp

## Install

```sh
agentstack add mcp-knuckles-team-documentdb-mcp
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Documentdb Mcp
## CLI or API | MCP | Agent

*Version: 1.0.1*

> **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](https://knuckles-team.github.io/documentdb-mcp/).

---

## Overview

**Documentdb Mcp** is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with DocumentDB MCP Server & A2A Server. DocumentDB is a MongoDB compatible open source document database built on PostgreSQL..

---

## 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:** Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
- **Integrated Graph Agent:** Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
- **Native Telemetry & Tracing:** Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

---

## CLI or API

This agent wraps the DocumentDB MCP Server & A2A Server. DocumentDB is a MongoDB compatible open source document database built on PostgreSQL. API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in [docs/index.md](docs/index.md).

---

## MCP

This server utilizes 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)._

#### Condensed action-routed tools (default — `MCP_TOOL_MODE=condensed`)

| MCP Tool | Toggle Env Var | Description |
|----------|----------------|-------------|
| `documentdb_analysis` | `ANALYSISTOOL` | Manage analysis operations. |
| `documentdb_collections` | `COLLECTIONSTOOL` | Manage collections operations. |
| `documentdb_crud` | `CRUDTOOL` | Manage crud operations. |
| `documentdb_system` | `SYSTEMTOOL` | Manage system operations. |
| `documentdb_users` | `USERSTOOL` | Manage users operations. |

#### Verbose 1:1 API-mapped tools (`MCP_TOOL_MODE=verbose` or `both`)

28 per-operation tools — one per public API method (click to expand)

| 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. |

_5 action-routed tool(s) (default) · 28 verbose 1:1 tool(s). Each is enabled unless its `TOOL` toggle is set false; `MCP_TOOL_MODE` selects the surface (`condensed` default · `verbose` 1:1 · `both`). Auto-generated — do not edit._

Detailed tool schemas, parameter shapes, and validation constraints are preserved in [docs/mcp.md](docs/mcp.md).

### Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

- **CLI Arguments:** Pass `--tools` or `--toolsets` (or their disabled counterparts `--disabled-tools` and `--disabled-toolsets`) during startup.
- **Environment Variables:** Define standard environment variables:
  - `MCP_ENABLED_TOOLS` / `MCP_DISABLED_TOOLS`
  - `MCP_ENABLED_TAGS` / `MCP_DISABLED_TAGS`
- **HTTP SSE Request Headers:** Pass custom headers during transport initialization:
  - `x-mcp-enabled-tools` / `x-mcp-disabled-tools`
  - `x-mcp-enabled-tags` / `x-mcp-disabled-tags`
- **HTTP SSE Request Query Parameters:** Append query parameters directly to your 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 slim `[mcp]` extra.** All examples install `documentdb-mcp[mcp]` — the
> MCP-server extra that pulls only the FastMCP / FastAPI tooling (`agent-utilities[mcp]`).
> It deliberately **excludes** the heavy agent runtime (`pydantic-ai`, the epistemic-graph
> engine, `dspy`, `llama-index`), so `uvx` / container installs are far smaller. Use the
> full `[agent]` extra only when you need the integrated Pydantic AI agent.

#### stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

```json
{
  "mcpServers": {
    "documentdb-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "documentdb-mcp[mcp]",
        "documentdb-mcp"
      ],
      "env": {
        "MCP_TOOL_MODE": "condensed",
        "ANALYSISTOOL": "True",
        "COLLECTIONSTOOL": "True",
        "CRUDTOOL": "True",
        "MONGODB_HOST": "localhost",
        "MONGODB_PORT": "27017",
        "MONGODB_URI": "mongodb://localhost:27017/",
        "SYSTEMTOOL": "True",
        "USERSTOOL": "True"
      }
    }
  }
}
```

#### Streamable-HTTP Transport (networked / production)

```json
{
  "mcpServers": {
    "documentdb-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "documentdb-mcp[mcp]",
        "documentdb-mcp",
        "--transport",
        "streamable-http",
        "--port",
        "8000"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "MCP_TOOL_MODE": "condensed",
        "ANALYSISTOOL": "True",
        "COLLECTIONSTOOL": "True",
        "CRUDTOOL": "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`:

```json
{
  "mcpServers": {
    "documentdb-mcp": {
      "url": "http://localhost:8000/documentdb-mcp/mcp"
    }
  }
}
```

Deploying the Streamable-HTTP server via Docker:

```bash
docker run -d \
  --name documentdb-mcp-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e HOST=0.0.0.0 \
  -e PORT=8000 \
  -e MCP_TOOL_MODE=condensed \
  -e ANALYSISTOOL=True \
  -e COLLECTIONSTOOL=True \
  -e CRUDTOOL=True \
  -e MONGODB_HOST=localhost \
  -e MONGODB_PORT=27017 \
  -e MONGODB_URI=mongodb://localhost:27017/ \
  -e SYSTEMTOOL=True \
  -e USERSTOOL=True \
  knucklessg1/documentdb-mcp:mcp
```

_Auto-generated from the code-read env surface (`MCP_TOOL_MODE` + package vars) — do not edit._

### Additional Deployment Options

`documentdb-mcp` can also run as a **local container** (Docker / Podman / `uv`) or be
consumed from a **remote deployment**. The
[Deployment guide](https://knuckles-team.github.io/documentdb-mcp/deployment/) has full, copy-paste
`mcp_config.json` for all four transports — **stdio**, **streamable-http**,
**local container / uv**, and **remote URL**:

- **Local container / uv** — launch the server from `mcp_config.json` via `uvx`,
  `docker run`, or `podman run`, or point at a local streamable-http container by `url`.
- **Remote URL** — connect to a server deployed behind Caddy at
  `http://documentdb-mcp.arpa/mcp` using the `"url"` key.

## Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the **Agent Control Protocol (ACP)** and interacts seamlessly with the **Agent Web UI (AG-UI)** and Terminal interface.

### Running the Agent CLI
To start the interactive command-line agent:

```bash
# Set credentials
export MONGODB_URI="mongodb://localhost:27017/"
export MONGODB_HOST="localhost"
export MONGODB_PORT="27017"

# Run the agent server
documentdb-agent --provider openai --model-id gpt-4o
```

### Docker Compose Orchestration
The following `docker/agent.compose.yml` configures the Agent, Web UI, and Terminal Interface together:

```yaml
version: '3.8'

services:
  documentdb-mcp-mcp:
    image: knucklessg1/documentdb-mcp:mcp
    container_name: documentdb-mcp-mcp
    hostname: documentdb-mcp-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  documentdb-mcp-agent:
    image: knucklessg1/documentdb-mcp:latest
    container_name: documentdb-mcp-agent
    hostname: documentdb-mcp-agent
    restart: always
    depends_on:
      - documentdb-mcp-mcp
    env_file:
      - ../.env
    command: [ "documentdb-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9015
      - MCP_URL=http://documentdb-mcp-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9015:9015"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9015/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

```

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in [docs/agent.md](docs/agent.md).

---

## Security & Governance

Built directly upon the enterprise-ready [`agent-utilities`](https://github.com/Knuckles-Team/agent-utilities) core, standard security parameters are fully supported:

### Access Control & Policy Enforcement
- **Eunomia Policies:** Fine-grained, policy-driven tool authorization. Supports `none`, local `embedded` (`mcp_policies.json`), or centralized `remote` modes.
- **OIDC Token Delegation:** Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
- **Scoped Credentials:** Execution context runs restricted to the specific caller identity.

### Runtime Security Grid
| Feature | Functionality | Enablement |
|---------|---------------|------------|
| **Tool Guard** | Sensitivity inspection with human-in-the-loop validation | Enabled by default |
| **Prompt Injection Defense** | Input scanning, repetition monitoring, and recursive loop blocks | Enabled by default |
| **Context Safety Guard** | Stuck-loop detectors and contextual overflow preemptive alerts | Enabled by default |

## Environment Variables

#### Package environment variables

| Variable | Example | Description |
|----------|---------|-------------|
| `HOST` | `0.0.0.0` |  |
| `PORT` | `8000` |  |
| `TRANSPORT` | `stdio` | options: stdio, streamable-http, sse |
| `ENABLE_OTEL` | `True` |  |
| `OTEL_EXPORTER_OTLP_ENDPOINT` | `http://localhost:8080/api/public/otel` |  |
| `OTEL_EXPORTER_OTLP_PUBLIC_KEY` | `pk-...` |  |
| `OTEL_EXPORTER_OTLP_SECRET_KEY` | `sk-...` |  |
| `OTEL_EXPORTER_OTLP_PROTOCOL` | `http/protobuf` |  |
| `EUNOMIA_TYPE` | `none` | options: none, embedded, remote |
| `EUNOMIA_POLICY_FILE` | `mcp_policies.json` |  |
| `EUNOMIA_REMOTE_URL` | `http://eunomia-server:8000` |  |
| `AUTH_TYPE` | `scram-sha-256` | options: scram-sha-1, scram-sha-256, standard, none |
| `MONGODB_URI` | `mongodb://localhost:27017/` |  |
| `MONGODB_HOST` | `localhost` |  |
| `MONGODB_PORT` | `27017` |  |
| `SYSTEMTOOL` | `True` |  |
| `COLLECTIONSTOOL` | `True` |  |
| `USERSTOOL` | `True` |  |
| `CRUDTOOL` | `True` |  |
| `ANALYSISTOOL` | `True` |  |

#### Inherited agent-utilities variables (apply to every connector)

| Variable | Example | Description |
|----------|---------|-------------|
| `MCP_TOOL_MODE` | `condensed` | Tool surface: `condensed` | `verbose` | `both` |
| `MCP_ENABLED_TOOLS` | — | Comma-separated tool allow-list |
| `MCP_DISABLED_TOOLS` | — | Comma-separated tool deny-list |
| `MCP_ENABLED_TAGS` | — | Comma-separated tag allow-list |
| `MCP_DISABLED_TAGS` | — | Comma-separated tag deny-list |
| `MCP_CLIENT_AUTH` | — | Outbound MCP auth (`oidc-client-credentials` for fleet calls) |
| `OIDC_CLIENT_ID` | — | OIDC client id (service-account auth) |
| `OIDC_CLIENT_SECRET` | — | OIDC client secret (service-account auth) |
| `DEBUG` | `False` | Verbose logging |
| `PYTHONUNBUFFERED` | `1` | Unbuffered stdout (recommended in containers) |
| `MCP_URL` | `http://localhost:8000/mcp` | URL of the MCP server the agent connects to |
| `PROVIDER` | `openai` | LLM provider for the agent |
| `MODEL_ID` | `gpt-4o` | Model id for the agent |
| `ENABLE_WEB_UI` | `True` | Serve the AG-UI web interface |

_20 package + 14 inherited variable(s). Auto-generated from `.env.example` + the shared agent-utilities set — do not edit._

Every variable the server reads, grouped by purpose.

### MCP server / transport
| Variable | Description | Default |
|----------|-------------|---------|
| `TRANSPORT` | `stdio`, `streamable-http`, or `sse` | `stdio` |
| `HOST` | Bind host (HTTP transports) | `0.0.0.0` |
| `PORT` | Bind port (HTTP transports) | `8000` |
| `MCP_TOOL_MODE` | Tool surface: `condensed`, `verbose`, or `both` | `condens

…

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Knuckles-Team](https://github.com/Knuckles-Team)
- **Source:** [Knuckles-Team/documentdb-mcp](https://github.com/Knuckles-Team/documentdb-mcp)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-knuckles-team-documentdb-mcp
- Seller: https://agentstack.voostack.com/s/knuckles-team
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.