MCP server for Obris — bring your saved references into AI conversations
Project description
Obris MCP Server
An MCP server that brings your saved Obris references into AI conversations on Claude, ChatGPT, Gemini, and any MCP-compatible client.
Features
- List projects — Browse all your Obris projects to find the one you need
- Pull in references — Retrieve saved bookmarks, highlights, and notes as context for any conversation
- Read-only — The server only reads your data; it never modifies anything in your Obris account
Setup
1. Get your API key
Generate an API key from your Obris dashboard. Don't have an account? Sign up.
2. Install and configure
Claude Desktop (Recommended)
Build and install the extension bundle:
npm install -g @anthropic-ai/mcpb
git clone https://github.com/obris-dev/obris-mcp.git
cd obris-mcp
mcpb pack .
Then in Claude Desktop, go to Settings > Extensions > Install Extension and select the generated obris-mcp.mcpb file. You'll be prompted to enter your API key during setup.
Claude Desktop (Manual config)
Alternatively, add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"obris": {
"command": "uvx",
"args": ["obris-mcp"],
"env": {
"OBRIS_API_KEY": "your_api_key_here"
}
}
}
}
Other MCP clients
# Install
pip install obris-mcp
# Set your API key
export OBRIS_API_KEY=your_api_key_here
# Run
obris-mcp
Tools
| Tool | Description |
|---|---|
list_projects |
List all your Obris projects |
get_project_references |
Get saved references for a specific project |
Examples
Example 1: Listing your projects
Prompt: "What Obris projects do I have?"
The list_projects tool is called and returns:
Projects:
- Marketing Strategy (id: proj_abc123)
- Product Roadmap (id: proj_def456)
- Competitive Analysis (id: proj_ghi789)
Example 2: Getting references for a project
Prompt: "Pull in my saved references for the Marketing Strategy project."
The list_projects tool is called first to find the project ID, then get_project_references is called with project_id: "proj_abc123":
### How to Build a Content Strategy
Content strategy starts with understanding your audience...
(source: https://example.com/content-strategy)
---
### SEO Best Practices 2025
Focus on search intent rather than keyword density...
(source: https://example.com/seo-guide)
Example 3: Using references as context for a task
Prompt: "Using my Competitive Analysis references, summarize the key differentiators of our top 3 competitors."
The list_projects tool finds the Competitive Analysis project, then get_project_references retrieves all saved references. The AI uses those references as context to generate a structured summary of competitor differentiators based on your saved research.
Development
# Clone and install
git clone https://github.com/obris-dev/obris-mcp.git
cd obris-mcp
cp .env.example .env # Add your API key
# Install with uv
uv sync
# Run locally
uv run obris-mcp
Privacy Policy
This server sends your Obris API key to the Obris API (api.obris.ai) to authenticate requests. It retrieves project and reference data from your account. No data is stored locally or sent to any third party.
For the full privacy policy, see obris.ai/privacy.
Support
For issues or questions, contact support@obris.ai or open an issue on GitHub.
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file obris_mcp-0.1.3.tar.gz.
File metadata
- Download URL: obris_mcp-0.1.3.tar.gz
- Upload date:
- Size: 63.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f5aa83a17c12533be98977a86041b47d0f61cbaa44317bf60d849da925bb8ee7
|
|
| MD5 |
1a8679c90de427e8314fb9bc7c3f8ab8
|
|
| BLAKE2b-256 |
dc0b7a364deee9a3b00bb1eca8533b54aca4b5fb861513e22ff8589ef7e7716c
|
File details
Details for the file obris_mcp-0.1.3-py3-none-any.whl.
File metadata
- Download URL: obris_mcp-0.1.3-py3-none-any.whl
- Upload date:
- Size: 6.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
04615e4128e07c96dabd6e388417497bd5be637dcd9002015c604b788385ece0
|
|
| MD5 |
86fb62a98432f3cda55de0cd6c4e170d
|
|
| BLAKE2b-256 |
7cb3cf7d29f56c37497aa5287b245c2610ce1f409303bc05a36b1cd34ccc240b
|