Skip to content
Back to search

mcp-server-qdrant

An official Qdrant Model Context Protocol (MCP) server implementation

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/qdrant--mcp-server-qdrant/badge.svg)](/listings/qdrant--mcp-server-qdrant)

HTML

<a href="/listings/qdrant--mcp-server-qdrant"><img src="/api/listings/qdrant--mcp-server-qdrant/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Using uvx

When using [`uvx`](https://docs.astral.sh/uv/guides/tools/#running-tools) no specific installation is needed to directly run *mcp-server-qdrant*.

QDRANT_URL="http://localhost:6333" \
COLLECTION_NAME="my-collection" \
EMBEDDING_MODEL="sentence-transformers/all-MiniLM-L6-v2" \
uvx mcp-server-qdrant

Transport Protocols

The server supports different transport protocols that can be specified using the `--transport` flag:

QDRANT_URL="http://localhost:6333" \
COLLECTION_NAME="my-collection" \
uvx mcp-server-qdrant --transport sse

Supported transport protocols:

- `stdio` (default): Standard input/output transport, might only be used by local MCP clients - `sse`: Server-Sent Events transport, perfect for remote clients - `streamable-http`: Streamable HTTP transport, perfect for remote clients, more recent than SSE

The default transport is `stdio` if not specified.

When SSE transport is used, the server will listen on the specified port and wait for incoming connections. The default port is 8000, however it can be changed using the `FASTMCP_SERVER_PORT` environment variable.

QDRANT_URL="http://localhost:6333" \
COLLECTION_NAME="my-collection" \
FASTMCP_SERVER_PORT=1234 \
uvx mcp-server-qdrant --transport sse

Using Docker

A Dockerfile is available for building and running the MCP server:

# Build the container
docker build -t mcp-server-qdrant .

# Run the container
docker run -p 8000:8000 \
  -e FASTMCP_SERVER_HOST="0.0.0.0" \
  -e QDRANT_URL="http://your-qdrant-server:6333" \
  -e QDRANT_API_KEY="your-api-key" \
  -e COLLECTION_NAME="your-collection" \
  mcp-server-qdrant

> [!TIP] > Please note that we set `FASTMCP_SERVER_HOST="0.0.0.0"` to make the server listen on all network interfaces. This is > necessary when running the server in a Docker container.

Installing via Smithery

To install Qdrant MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/protocol/mcp-server-qdrant):

npx @smithery/cli install mcp-server-qdrant --client claude

Manual configuration of Claude Desktop

To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your `claude_desktop_config.json`:

{
  "qdrant": {
    "command": "uvx",
    "args": ["mcp-server-qdrant"],
    "env": {
      "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
      "QDRANT_API_KEY": "your_api_key",
      "COLLECTION_NAME": "your-collection-name",
      "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
    }
  }
}

For local Qdrant mode:

{
  "qdrant": {
    "command": "uvx",
    "args": ["mcp-server-qdrant"],
    "env": {
      "QDRANT_LOCAL_PATH": "/path/to/qdrant/database",
      "COLLECTION_NAME": "your-collection-name",
      "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
    }
  }
}

This MCP server will automatically create a collection with the specified name if it doesn't exist.

By default, the server will use the `sentence-transformers/all-MiniLM-L6-v2` embedding model to encode memories. For the time being, only [FastEmbed](https://qdrant.github.io/fastembed/) models are supported.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 492 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # mcp-server-qdrant: A Qdrant MCP server
  2. [![smithery badge](https://smithery.ai/badge/mcp-server-qdrant)](https://smithery.ai/protocol/mcp-server-qdrant)
  3. > The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open protocol that enables
  4. > seamless integration between LLM applications and external data sources and tools. Whether you're building an
  5. > AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to
  6. > connect LLMs with the context they need.
  7. This repository is an example of how to create a MCP server for [Qdrant](https://qdrant.tech/), a vector search engine.
  8. ## Overview
  9. An official Model Context Protocol server for keeping and retrieving memories in the Qdrant vector search engine.
  10. It acts as a semantic memory layer on top of the Qdrant database.
  11. ## Components
  12. ### Tools
  13. 1. `qdrant-store`
  14. - Store some information in the Qdrant database
  15. - Input:
  16. - `information` (string): Information to store
  17. - `metadata` (JSON): Optional metadata to store
  18. - `collection_name` (string): Name of the collection to store the information in. This field is required if there are no default collection name.
  19. If there is a default collection name, this field is not enabled.
  20. - Returns: Confirmation message
  21. 2. `qdrant-find`
  22. - Retrieve relevant information from the Qdrant database
  23. - Input:
  24. - `query` (string): Query to use for searching
  25. - `collection_name` (string): Name of the collection to store the information in. This field is required if there are no default collection name.
  26. If there is a default collection name, this field is not enabled.
  27. - Returns: Information stored in the Qdrant database as separate messages
  28. ## Environment Variables
  29. Configuration is done via environment variables. The only command-line argument is `--transport`, used to select the [transport protocol](#transport-protocols).
  30. > [!NOTE]
  31. > You cannot provide both `QDRANT_URL` and `QDRANT_LOCAL_PATH` at the same time.
  32. | Name | Description | Default Value |
  33. |--------------------------|---------------------------------------------------------------------|-------------------------------------------------------------------|
  34. | `QDRANT_URL` | URL of the Qdrant server | None |
  35. | `QDRANT_API_KEY` | API key for the Qdrant server | None |
  36. | `COLLECTION_NAME` | Name of the default collection to use. | None |
  37. | `QDRANT_LOCAL_PATH` | Path to the local Qdrant database (alternative to `QDRANT_URL`) | None |
  38. | `EMBEDDING_PROVIDER` | Embedding provider to use (currently only "fastembed" is supported) | `fastembed` |
  39. | `EMBEDDING_MODEL` | Name of the embedding model to use | `sentence-transformers/all-MiniLM-L6-v2` |
  40. | `TOOL_STORE_DESCRIPTION` | Custom description for the store tool | See default in [`settings.py`](src/mcp_server_qdrant/settings.py) |
  41. | `TOOL_FIND_DESCRIPTION` | Custom description for the find tool | See default in [`settings.py`](src/mcp_server_qdrant/settings.py) |
  42. | `QDRANT_SEARCH_LIMIT` | Maximum number of results to return from search | `10` |
  43. | `QDRANT_READ_ONLY` | Enable read-only mode (disables `qdrant-store` tool) | `false` |
  44. ### FastMCP Environment Variables
  45. Since `mcp-server-qdrant` is based on FastMCP, it also supports all the FastMCP environment variables. The most
  46. important ones are listed below:
  47. | Environment Variable | Description | Default Value |
  48. |------------------------------|-----------------------------------------------------------------|---------------|
  49. | `FASTMCP_LOG_LEVEL` | Set logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) | `INFO` |
  50. | `FASTMCP_DEBUG` | Enable debug mode | `false` |
  51. | `FASTMCP_HOST` | Host address to bind the server to (SSE and HTTP transports) | `127.0.0.1` |
  52. | `FASTMCP_PORT` | Port to run the server on (SSE and HTTP transports) | `8000` |
  53. | `FASTMCP_MASK_ERROR_DETAILS` | Hide exception details from tool error messages sent to clients | `false` |
  54. > [!NOTE]
  55. > Before version 0.9.0, these settings used the `FASTMCP_SERVER_` prefix, for example `FASTMCP_SERVER_HOST`.
  56. > The old `FASTMCP_SERVER_HOST`, `FASTMCP_SERVER_PORT`, and `FASTMCP_SERVER_DEBUG` names still work but are deprecated
  57. > and will be removed in a future release. If both names are set, the new one wins.
  58. ## Installation
  59. ### Using uvx
  60. When using [`uvx`](https://docs.astral.sh/uv/guides/tools/#running-tools) no specific installation is needed to directly run *mcp-server-qdrant*.
  61. ```shell
  62. QDRANT_URL="http://localhost:6333" \
  63. COLLECTION_NAME="my-collection" \
  64. EMBEDDING_MODEL="sentence-transformers/all-MiniLM-L6-v2" \
  65. uvx mcp-server-qdrant
  66. ```
  67. #### Transport Protocols
  68. The server supports different transport protocols that can be specified using the `--transport` flag:
  69. ```shell
  70. QDRANT_URL="http://localhost:6333" \
  71. COLLECTION_NAME="my-collection" \
  72. uvx mcp-server-qdrant --transport sse
  73. ```
  74. Supported transport protocols:
  75. - `stdio` (default): Standard input/output transport, might only be used by local MCP clients
  76. - `sse`: Server-Sent Events transport, perfect for remote clients
  77. - `streamable-http`: Streamable HTTP transport, perfect for remote clients, more recent than SSE
  78. The default transport is `stdio` if not specified.
  79. When SSE transport is used, the server will listen on the specified port and wait for incoming connections. The default
  80. port is 8000, however it can be changed using the `FASTMCP_PORT` environment variable.
  81. ```shell
  82. QDRANT_URL="http://localhost:6333" \
  83. COLLECTION_NAME="my-collection" \
  84. FASTMCP_PORT=1234 \
  85. uvx mcp-server-qdrant --transport sse
  86. ```
  87. ### Using Docker
  88. A Dockerfile is available for building and running the MCP server:
  89. ```bash
  90. # Build the container
  91. docker build -t mcp-server-qdrant .
  92. # Run the container
  93. docker run -p 8000:8000 \
  94. -e FASTMCP_HOST="0.0.0.0" \
  95. -e QDRANT_URL="http://your-qdrant-server:6333" \
  96. -e QDRANT_API_KEY="your-api-key" \
  97. -e COLLECTION_NAME="your-collection" \
  98. mcp-server-qdrant
  99. ```
  100. > [!TIP]
  101. > Please note that we set `FASTMCP_HOST="0.0.0.0"` to make the server listen on all network interfaces. This is
  102. > necessary when running the server in a Docker container.
  103. ### Installing via Smithery
  104. To install Qdrant MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/protocol/mcp-server-qdrant):
  105. ```bash
  106. npx @smithery/cli install mcp-server-qdrant --client claude
  107. ```
  108. ### Manual configuration of Claude Desktop
  109. To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your
  110. `claude_desktop_config.json`:
  111. ```json
  112. {
  113. "qdrant": {
  114. "command": "uvx",
  115. "args": ["mcp-server-qdrant"],
  116. "env": {
  117. "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
  118. "QDRANT_API_KEY": "your_api_key",
  119. "COLLECTION_NAME": "your-collection-name",
  120. "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
  121. }
  122. }
  123. }
  124. ```
  125. For local Qdrant mode:
  126. ```json
  127. {
  128. "qdrant": {
  129. "command": "uvx",
  130. "args": ["mcp-server-qdrant"],
  131. "env": {
  132. "QDRANT_LOCAL_PATH": "/path/to/qdrant/database",
  133. "COLLECTION_NAME": "your-collection-name",
  134. "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
  135. }
  136. }
  137. }
  138. ```
  139. This MCP server will automatically create a collection with the specified name if it doesn't exist.
  140. By default, the server will use the `sentence-transformers/all-MiniLM-L6-v2` embedding model to encode memories.
  141. For the time being, only [FastEmbed](https://qdrant.github.io/fastembed/) models are supported.
  142. ## Support for other tools
  143. This MCP server can be used with any MCP-compatible client. For example, you can use it with
  144. [Cursor](https://docs.cursor.com/context/model-context-protocol) and [VS Code](https://code.visualstudio.com/docs), which provide built-in support for the Model Context
  145. Protocol.
  146. ### Using with Cursor/Windsurf
  147. You can configure this MCP server to work as a code search tool for Cursor or Windsurf by customizing the tool
  148. descriptions:
  149. ```bash
  150. QDRANT_URL="http://localhost:6333" \
  151. COLLECTION_NAME="code-snippets" \
  152. TOOL_STORE_DESCRIPTION="Store reusable code snippets for later retrieval. \
  153. The 'information' parameter should contain a natural language description of what the code does, \
  154. while the actual code should be included in the 'metadata' parameter as a 'code' property. \
  155. The value of 'metadata' is a Python dictionary with strings as keys. \
  156. Use this whenever you generate some code snippet." \
  157. TOOL_FIND_DESCRIPTION="Search for relevant code snippets based on natural language descriptions. \
  158. The 'query' parameter should describe what you're looking for, \
  159. and the tool will return the most relevant code snippets. \
  160. Use this when you need to find existing code snippets for reuse or reference." \
  161. uvx mcp-server-qdrant --transport sse # Enable SSE transport
  162. ```
  163. In Cursor/Windsurf, you can then configure the MCP server in your settings by pointing to this running server using
  164. SSE transport protocol. The description on how to add an MCP server to Cursor can be found in the [Cursor
  165. documentation](https://docs.cursor.com/context/model-context-protocol#adding-an-mcp-server-to-cursor). If you are
  166. running Cursor/Windsurf locally, you can use the following URL:
  167. ```
  168. http://localhost:8000/sse
  169. ```
  170. > [!TIP]
  171. > We suggest SSE transport as a preferred way to connect Cursor/Windsurf to the MCP server, as it can support remote
  172. > connections. That makes it easy to share the server with your team or use it in a cloud environment.
  173. This configuration transforms the Qdrant MCP server into a specialized code search tool that can:
  174. 1. Store code snippets, documentation, and implementation details
  175. 2. Retrieve relevant code examples based on semantic search
  176. 3. Help developers find specific implementations or usage patterns
  177. You can populate the database by storing natural language descriptions of code snippets (in the `information` parameter)
  178. along with the actual code (in the `metadata.code` property), and then search for them using natural language queries
  179. that describe what you're looking for.
  180. > [!NOTE]
  181. > The tool descriptions provided above are examples and may need to be customized for your specific use case. Consider
  182. > adjusting the descriptions to better match your team's workflow and the specific types of code snippets you want to
  183. > store and retrieve.
  184. **If you have successfully installed the `mcp-server-qdrant`, but still can't get it to work with Cursor, please
  185. consider creating the [Cursor rules](https://docs.cursor.com/context/rules-for-ai) so the MCP tools are always used when
  186. the agent produces a new code snippet.** You can restrict the rules to only work for certain file types, to avoid using
  187. the MCP server for the documentation or other types of content.
  188. ### Using with Claude Code
  189. You can enhance Claude Code's capabilities by connecting it to this MCP server, enabling semantic search over your
  190. existing codebase.
  191. #### Setting up mcp-server-qdrant
  192. 1. Add the MCP server to Claude Code:
  193. ```shell
  194. # Add mcp-server-qdrant configured for code search
  195. claude mcp add code-search \
  196. -e QDRANT_URL="http://localhost:6333" \
  197. -e COLLECTION_NAME="code-repository" \
  198. -e EMBEDDING_MODEL="sentence-transformers/all-MiniLM-L6-v2" \
  199. -e TOOL_STORE_DESCRIPTION="Store code snippets with descriptions. The 'information' parameter should contain a natural language description of what the code does, while the actual code should be included in the 'metadata' parameter as a 'code' property." \
  200. -e TOOL_FIND_DESCRIPTION="Search for relevant code snippets using natural language. The 'query' parameter should describe the functionality you're looking for." \
  201. -- uvx mcp-server-qdrant
  202. ```
  203. 2. Verify the server was added:
  204. ```shell
  205. claude mcp list
  206. ```
  207. #### Using Semantic Code Search in Claude Code
  208. Tool descriptions, specified in `TOOL_STORE_DESCRIPTION` and `TOOL_FIND_DESCRIPTION`, guide Claude Code on how to use
  209. the MCP server. The ones provided above are examples and may need to be customized for your specific use case. However,
  210. Claude Code should be already able to:
  211. 1. Use the `qdrant-store` tool to store code snippets with descriptions.
  212. 2. Use the `qdrant-find` tool to search for relevant code snippets using natural language.
  213. ### Run MCP server in Development Mode
  214. The MCP server can be run in development mode using the `mcp dev` command. This will start the server and open the MCP
  215. inspector in your browser.
  216. ```shell
  217. COLLECTION_NAME=mcp-dev fastmcp dev src/mcp_server_qdrant/server.py
  218. ```
  219. ### Using with VS Code
  220. For one-click installation, click one of the install buttons below:
  221. [![Install with UVX in VS Code](https://img.shields.io/badge/VS_Code-UVX-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=qdrant&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mcp-server-qdrant%22%5D%2C%22env%22%3A%7B%22QDRANT_URL%22%3A%22%24%7Binput%3AqdrantUrl%7D%22%2C%22QDRANT_API_KEY%22%3A%22%24%7Binput%3AqdrantApiKey%7D%22%2C%22COLLECTION_NAME%22%3A%22%24%7Binput%3AcollectionName%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantUrl%22%2C%22description%22%3A%22Qdrant+URL%22%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantApiKey%22%2C%22description%22%3A%22Qdrant+API+Key%22%2C%22password%22%3Atrue%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22collectionName%22%2C%22description%22%3A%22Collection+Name%22%7D%5D) [![Install with UVX in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-UVX-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=qdrant&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mcp-server-qdrant%22%5D%2C%22env%22%3A%7B%22QDRANT_URL%22%3A%22%24%7Binput%3AqdrantUrl%7D%22%2C%22QDRANT_API_KEY%22%3A%22%24%7Binput%3AqdrantApiKey%7D%22%2C%22COLLECTION_NAME%22%3A%22%24%7Binput%3AcollectionName%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantUrl%22%2C%22description%22%3A%22Qdrant+URL%22%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantApiKey%22%2C%22description%22%3A%22Qdrant+API+Key%22%2C%22password%22%3Atrue%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22collectionName%22%2C%22description%22%3A%22Collection+Name%22%7D%5D&quality=insiders)
  222. [![Install with Docker in VS Code](https://img.shields.io/badge/VS_Code-Docker-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=qdrant&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-p%22%2C%228000%3A8000%22%2C%22-i%22%2C%22--rm%22%2C%22-e%22%2C%22QDRANT_URL%22%2C%22-e%22%2C%22QDRANT_API_KEY%22%2C%22-e%22%2C%22COLLECTION_NAME%22%2C%22mcp-server-qdrant%22%5D%2C%22env%22%3A%7B%22QDRANT_URL%22%3A%22%24%7Binput%3AqdrantUrl%7D%22%2C%22QDRANT_API_KEY%22%3A%22%24%7Binput%3AqdrantApiKey%7D%22%2C%22COLLECTION_NAME%22%3A%22%24%7Binput%3AcollectionName%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantUrl%22%2C%22description%22%3A%22Qdrant+URL%22%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantApiKey%22%2C%22description%22%3A%22Qdrant+API+Key%22%2C%22password%22%3Atrue%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22collectionName%22%2C%22description%22%3A%22Collection+Name%22%7D%5D) [![Install with Docker in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Docker-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=qdrant&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-p%22%2C%228000%3A8000%22%2C%22-i%22%2C%22--rm%22%2C%22-e%22%2C%22QDRANT_URL%22%2C%22-e%22%2C%22QDRANT_API_KEY%22%2C%22-e%22%2C%22COLLECTION_NAME%22%2C%22mcp-server-qdrant%22%5D%2C%22env%22%3A%7B%22QDRANT_URL%22%3A%22%24%7Binput%3AqdrantUrl%7D%22%2C%22QDRANT_API_KEY%22%3A%22%24%7Binput%3AqdrantApiKey%7D%22%2C%22COLLECTION_NAME%22%3A%22%24%7Binput%3AcollectionName%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantUrl%22%2C%22description%22%3A%22Qdrant+URL%22%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantApiKey%22%2C%22description%22%3A%22Qdrant+API+Key%22%2C%22password%22%3Atrue%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22collectionName%22%2C%22description%22%3A%22Collection+Name%22%7D%5D&quality=insiders)
  223. #### Manual Installation
  224. Add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing `Ctrl + Shift + P` and typing `Preferences: Open User Settings (JSON)`.
  225. ```json
  226. {
  227. "mcp": {
  228. "inputs": [
  229. {
  230. "type": "promptString",
  231. "id": "qdrantUrl",
  232. "description": "Qdrant URL"
  233. },
  234. {
  235. "type": "promptString",
  236. "id": "qdrantApiKey",
  237. "description": "Qdrant API Key",
  238. "password": true
  239. },
  240. {
  241. "type": "promptString",
  242. "id": "collectionName",
  243. "description": "Collection Name"
  244. }
  245. ],
  246. "servers": {
  247. "qdrant": {
  248. "command": "uvx",
  249. "args": ["mcp-server-qdrant"],
  250. "env": {
  251. "QDRANT_URL": "${input:qdrantUrl}",
  252. "QDRANT_API_KEY": "${input:qdrantApiKey}",
  253. "COLLECTION_NAME": "${input:collectionName}"
  254. }
  255. }
  256. }
  257. }
  258. }
  259. ```
  260. Or if you prefer using Docker, add this configuration instead:
  261. ```json
  262. {
  263. "mcp": {
  264. "inputs": [
  265. {
  266. "type": "promptString",
  267. "id": "qdrantUrl",
  268. "description": "Qdrant URL"
  269. },
  270. {
  271. "type": "promptString",
  272. "id": "qdrantApiKey",
  273. "description": "Qdrant API Key",
  274. "password": true
  275. },
  276. {
  277. "type": "promptString",
  278. "id": "collectionName",
  279. "description": "Collection Name"
  280. }
  281. ],
  282. "servers": {
  283. "qdrant": {
  284. "command": "docker",
  285. "args": [
  286. "run",
  287. "-p", "8000:8000",
  288. "-i",
  289. "--rm",
  290. "-e", "QDRANT_URL",
  291. "-e", "QDRANT_API_KEY",
  292. "-e", "COLLECTION_NAME",
  293. "mcp-server-qdrant"
  294. ],
  295. "env": {
  296. "QDRANT_URL": "${input:qdrantUrl}",
  297. "QDRANT_API_KEY": "${input:qdrantApiKey}",
  298. "COLLECTION_NAME": "${input:collectionName}"
  299. }
  300. }
  301. }
  302. }
  303. }
  304. ```
  305. Alternatively, you can create a `.vscode/mcp.json` file in your workspace with the following content:
  306. ```json
  307. {
  308. "inputs": [
  309. {
  310. "type": "promptString",
  311. "id": "qdrantUrl",
  312. "description": "Qdrant URL"
  313. },
  314. {
  315. "type": "promptString",
  316. "id": "qdrantApiKey",
  317. "description": "Qdrant API Key",
  318. "password": true
  319. },
  320. {
  321. "type": "promptString",
  322. "id": "collectionName",
  323. "description": "Collection Name"
  324. }
  325. ],
  326. "servers": {
  327. "qdrant": {
  328. "command": "uvx",
  329. "args": ["mcp-server-qdrant"],
  330. "env": {
  331. "QDRANT_URL": "${input:qdrantUrl}",
  332. "QDRANT_API_KEY": "${input:qdrantApiKey}",
  333. "COLLECTION_NAME": "${input:collectionName}"
  334. }
  335. }
  336. }
  337. }
  338. ```
  339. For workspace configuration with Docker, use this in `.vscode/mcp.json`:
  340. ```json
  341. {
  342. "inputs": [
  343. {
  344. "type": "promptString",
  345. "id": "qdrantUrl",
  346. "description": "Qdrant URL"
  347. },
  348. {
  349. "type": "promptString",
  350. "id": "qdrantApiKey",
  351. "description": "Qdrant API Key",
  352. "password": true
  353. },
  354. {
  355. "type": "promptString",
  356. "id": "collectionName",
  357. "description": "Collection Name"
  358. }
  359. ],
  360. "servers": {
  361. "qdrant": {
  362. "command": "docker",
  363. "args": [
  364. "run",
  365. "-p", "8000:8000",
  366. "-i",
  367. "--rm",
  368. "-e", "QDRANT_URL",
  369. "-e", "QDRANT_API_KEY",
  370. "-e", "COLLECTION_NAME",
  371. "mcp-server-qdrant"
  372. ],
  373. "env": {
  374. "QDRANT_URL": "${input:qdrantUrl}",
  375. "QDRANT_API_KEY": "${input:qdrantApiKey}",
  376. "COLLECTION_NAME": "${input:collectionName}"
  377. }
  378. }
  379. }
  380. }
  381. ```
  382. ## Contributing
  383. If you have suggestions for how mcp-server-qdrant could be improved, or want to report a bug, open an issue!
  384. We'd love all and any contributions.
  385. ### Testing `mcp-server-qdrant` locally
  386. The [MCP inspector](https://github.com/modelcontextprotocol/inspector) is a developer tool for testing and debugging MCP
  387. servers. It runs both a client UI (default port 5173) and an MCP proxy server (default port 3000). Open the client UI in
  388. your browser to use the inspector.
  389. ```shell
  390. QDRANT_URL=":memory:" COLLECTION_NAME="test" \
  391. fastmcp dev src/mcp_server_qdrant/server.py
  392. ```
  393. Once started, open your browser to http://localhost:5173 to access the inspector interface.
  394. ## License
  395. This MCP server is licensed under the Apache License 2.0. This means you are free to use, modify, and distribute the
  396. software, subject to the terms and conditions of the Apache License 2.0. For more details, please see the LICENSE file
  397. in the project repository.
  398. ## Privacy and support
  399. - [Privacy Policy](https://qdrant.tech/legal/privacy-policy/)
  400. - [Support](https://github.com/qdrant/mcp-server-qdrant/issues)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.