# AIND Metadata MCP Server
[](LICENSE)
[](https://github.com/semantic-release/semantic-release)
An MCP (Model Context Protocol) server that provides access to AIND (Allen Institute for Neural Dynamics) metadata and data assets through a comprehensive set of tools and resources.
## Features
This MCP server provides tools for:
- **Data Retrieval**: Query MongoDB collections with filters and projections
- **Aggregation**: Execute complex MongoDB aggregation pipelines
- **Schema Exploration**: Access detailed schema examples and documentation
- **NWB File Access**: Load and explore NWB (Neurodata Without Borders) files
- **Data Summaries**: Generate AI-powered summaries of data assets
## Installation
Install uv if you haven't already - following [this documentation](https://docs.astral.sh/uv/getting-started/installation/)
Install the MCP server using uv:
```bash
uv tool install aind-metadata-mcp
```
Or using pip:
```bash
pip install aind-metadata-mcp
```
## Configuration
### For Cline (VSCode Extension)
In order to ensure that the MCP server runs in your preferred client, you will have to download the `aind-metadata-mcp` package to your console. If space is an issue, please set `UV_CACHE_DIR` and `UV_TOOL_DIR` to locations that have capacity before proceeding with the next step.
1. Simpler version of install
Run `uv tool install aind-metadata-mcp` on your terminal and proceed below to configuring your MCP clients.
2. If the above step didn't work:
Create virtual environment with python 3.11 in IDE
```bash
# Instructions for Conda
conda create -n <my_env> python=3.11
conda activate <my_env>
# Instructions for virtual environment
py -3.11 -m venv .venv
# Windows startup
.venv\Scripts\Activate.ps1
# Mac/ Linux startup
source .venv/bin/activate
```
Run the following commands in your IDE terminal.
```bash
pip install uv
uvx aind-metadata-mcp
```
If all goes well, and you see the following notice - `Starting MCP server 'aind_data_access' with transport 'stdio'`-, you should be good for the set up in your client of choice!
## Instructions for use in MCP clients
JSON Config files to add MCP servers in clients should be structured like this
```bash
{
"mcpServers": {
}
}
```
Insert the following lines into the mcpServers dictionary
```bash
"aind_data_access": {
"disabled": false,
"timeout": 300,
"type": "stdio",
"command": "aind-metadata-mcp"
}
```
Note that after configuring the JSON files, it will take a few minutes for the serve to populate in the client.
### Claude Desktop App
- Click the three lines at the top left of the screen.
- File > Settings > Developer > Edit config
### Cline in VSCode
- Ensure that Cline is downloaded to VScode
- Click the three stacked rectangles at the top right of the Cline window
- Installed > Configure MCP Servers
- Close and reopen VSCode
### Github Copilot in VSCode
- Command palette (ctr shift p)
- Search for MCP: Add server
- Select `Manual Install` / `stdio`
- When prompted for a command, input `uvx aind-data-access`
- Name your server
- Close and reopen VSCode
- In Copilot chat -> Select agent mode -> Click the three stacked rectangles to configure tools
- In order to enable the agent to reply with context of the AIND API, you'll have to manually add the .txt files (under resources) in this repository
### For use in Code Ocean
* Locate the [following capsule](https://codeocean.allenneuraldynamics.org/capsule/7008682/tree), to spin up Cline and Co-pilot with the aind-metadata-mcp pre-installed.
* Refer the the [code ocean MCP server](https://github.com/codeocean/codeocean-mcp-server) for additional support
* Either pin version 4.2, or 4.5
Raw data
{
"_id": null,
"home_page": null,
"name": "aind-metadata-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": null,
"author": "Allen Institute for Neural Dynamics",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/d9/bc/71860fa42e9fc98d766d3918d984b21517361a6cb941e6d18746b5ada065/aind_metadata_mcp-0.5.1.tar.gz",
"platform": null,
"description": "# AIND Metadata MCP Server\n\n[](LICENSE)\n\n[](https://github.com/semantic-release/semantic-release)\n\n\n\n\nAn MCP (Model Context Protocol) server that provides access to AIND (Allen Institute for Neural Dynamics) metadata and data assets through a comprehensive set of tools and resources.\n\n## Features\n\nThis MCP server provides tools for:\n\n- **Data Retrieval**: Query MongoDB collections with filters and projections\n- **Aggregation**: Execute complex MongoDB aggregation pipelines\n- **Schema Exploration**: Access detailed schema examples and documentation\n- **NWB File Access**: Load and explore NWB (Neurodata Without Borders) files\n- **Data Summaries**: Generate AI-powered summaries of data assets\n\n## Installation\n\nInstall uv if you haven't already - following [this documentation](https://docs.astral.sh/uv/getting-started/installation/)\n\nInstall the MCP server using uv:\n\n```bash\nuv tool install aind-metadata-mcp\n```\n\nOr using pip:\n\n```bash\npip install aind-metadata-mcp\n```\n\n## Configuration\n\n### For Cline (VSCode Extension)\n\nIn order to ensure that the MCP server runs in your preferred client, you will have to download the `aind-metadata-mcp` package to your console. If space is an issue, please set `UV_CACHE_DIR` and `UV_TOOL_DIR` to locations that have capacity before proceeding with the next step.\n\n1. Simpler version of install\n Run `uv tool install aind-metadata-mcp` on your terminal and proceed below to configuring your MCP clients.\n\n2. If the above step didn't work:\n\nCreate virtual environment with python 3.11 in IDE\n\n```bash\n# Instructions for Conda\nconda create -n <my_env> python=3.11\nconda activate <my_env>\n\n# Instructions for virtual environment\npy -3.11 -m venv .venv\n# Windows startup\n.venv\\Scripts\\Activate.ps1 \n# Mac/ Linux startup\nsource .venv/bin/activate \n```\n\nRun the following commands in your IDE terminal.\n\n```bash\npip install uv\nuvx aind-metadata-mcp\n```\n\nIf all goes well, and you see the following notice - `Starting MCP server 'aind_data_access' with transport 'stdio'`-, you should be good for the set up in your client of choice!\n\n## Instructions for use in MCP clients\n\nJSON Config files to add MCP servers in clients should be structured like this\n\n```bash\n{\n \"mcpServers\": {\n\n }\n}\n```\n\nInsert the following lines into the mcpServers dictionary\n\n```bash\n\n\"aind_data_access\": {\n \"disabled\": false,\n \"timeout\": 300,\n \"type\": \"stdio\",\n \"command\": \"aind-metadata-mcp\"\n}\n```\n\nNote that after configuring the JSON files, it will take a few minutes for the serve to populate in the client.\n\n### Claude Desktop App\n\n- Click the three lines at the top left of the screen.\n- File > Settings > Developer > Edit config\n\n### Cline in VSCode\n\n- Ensure that Cline is downloaded to VScode\n- Click the three stacked rectangles at the top right of the Cline window\n- Installed > Configure MCP Servers\n- Close and reopen VSCode\n\n### Github Copilot in VSCode\n\n- Command palette (ctr shift p)\n- Search for MCP: Add server\n- Select `Manual Install` / `stdio`\n- When prompted for a command, input `uvx aind-data-access`\n- Name your server\n- Close and reopen VSCode\n- In Copilot chat -> Select agent mode -> Click the three stacked rectangles to configure tools\n- In order to enable the agent to reply with context of the AIND API, you'll have to manually add the .txt files (under resources) in this repository\n\n### For use in Code Ocean\n\n* Locate the [following capsule](https://codeocean.allenneuraldynamics.org/capsule/7008682/tree), to spin up Cline and Co-pilot with the aind-metadata-mcp pre-installed.\n* Refer the the [code ocean MCP server](https://github.com/codeocean/codeocean-mcp-server) for additional support\n* Either pin version 4.2, or 4.5\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "MCP server for AIND metadata",
"version": "0.5.1",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "7e30718e1be2bd9fd66c2894f53cc5d68660e38e2f7d79eafc8ecb876bb0f471",
"md5": "d0387291c9ab67e6e8cc597e6b0e6636",
"sha256": "9dc31019eaa9bb5797b016697ff6c202355c29e717ffed1cdf5c052f504d47d4"
},
"downloads": -1,
"filename": "aind_metadata_mcp-0.5.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d0387291c9ab67e6e8cc597e6b0e6636",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 37137,
"upload_time": "2025-08-29T18:58:44",
"upload_time_iso_8601": "2025-08-29T18:58:44.671718Z",
"url": "https://files.pythonhosted.org/packages/7e/30/718e1be2bd9fd66c2894f53cc5d68660e38e2f7d79eafc8ecb876bb0f471/aind_metadata_mcp-0.5.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d9bc71860fa42e9fc98d766d3918d984b21517361a6cb941e6d18746b5ada065",
"md5": "81455e178f44e2c991ac1efd8786c7ff",
"sha256": "3cf6ed41817f1e9d67143a4d1a7ca93f847452f60dcdf673b321cf0225ece251"
},
"downloads": -1,
"filename": "aind_metadata_mcp-0.5.1.tar.gz",
"has_sig": false,
"md5_digest": "81455e178f44e2c991ac1efd8786c7ff",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 153998,
"upload_time": "2025-08-29T18:58:45",
"upload_time_iso_8601": "2025-08-29T18:58:45.654394Z",
"url": "https://files.pythonhosted.org/packages/d9/bc/71860fa42e9fc98d766d3918d984b21517361a6cb941e6d18746b5ada065/aind_metadata_mcp-0.5.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-29 18:58:45",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "aind-metadata-mcp"
}
JSON