Obris MCP Server

1# Obris MCP Server
2 
3<!-- mcp-name: ai.obris/mcp -->
4 
5An [MCP](https://modelcontextprotocol.io/) server that brings your curated [Obris](https://obris.ai) knowledge into any AI conversation. Use the [Chrome extension](https://chromewebstore.google.com/detail/obris-%E2%80%93-save-key-content/kkkiblfabiopcmoghfcjffiobjlppfdp) or upload directly to save knowledge to dedicated topics so you never start another AI chat from zero again.
6 
7## Features
8 
9- **List topics** — Browse all your Obris topics to find the one you need
10- **Pull in knowledge** — Retrieve saved bookmarks, highlights, and notes as context for any conversation
11- **Save knowledge** — Capture takeaways and notes from conversations to reuse in future chats
12 
13## Setup
14 
15### 1. Get your API key
16 
17Generate an API key from your [Obris dashboard](https://app.obris.ai/api-keys). Don't have an account? [Sign up](https://app.obris.ai/signup).
18 
19### 2. Install and configure
20 
21#### Claude Desktop
22 
23Add your API key to your shell profile (`~/.zshrc`, `~/.zprofile`, or `~/.bash_profile`):
24 
25```bash
26export OBRIS_API_KEY=your_api_key_here
27```
28 
29Then reload your shell:
30 
31```bash
32source ~/.zshrc
33```
34 
35Open Claude Desktop settings → **Developer** → **Edit Config**, and add the following to `claude_desktop_config.json`:
36 
37```json
38{
39  "mcpServers": {
40    "obris": {
41      "command": "/full/path/to/uvx",
42      "args": ["obris-mcp"],
43      "env": {
44        "OBRIS_API_KEY": "$OBRIS_API_KEY"
45      }
46    }
47  }
48}
49```
50 
51> Run `which uvx` to get the full path for `"command"`.
52 
53Restart Claude Desktop to pick up the changes.
54 
55#### Claude Code
56 
57```bash
58claude mcp add Obris -e OBRIS_API_KEY=$OBRIS_API_KEY --transport stdio -- uvx obris-mcp
59```
60 
61Start a new conversation and type `/mcp` to verify the Obris server is connected.
62 
63#### Gemini CLI
64 
65```bash
66gemini mcp add -e OBRIS_API_KEY=$OBRIS_API_KEY --transport stdio Obris uvx obris-mcp
67```
68 
69Start a new Gemini session and run `/mcp` to verify the Obris server is connected.
70 
71#### Other MCP clients
72 
73See the [local MCP setup guide](https://docs.obris.ai/guides/local-mcp) for more options.
74 
75## Tools
76 
77| Tool | Description |
78|------|-------------|
79| `list_topics` | List all your Obris topics |
80| `get_topic_knowledge` | Get saved knowledge for a specific topic |
81| `create_topic` | Create a new topic to organize knowledge |
82| `add_knowledge` | Save text knowledge to a topic |
83 
84## Examples
85 
86### Example 1: Listing your topics
87 
88**Prompt:** "What Obris topics do I have?"
89 
90The `list_topics` tool is called and returns:
91 
92```
93Topics:
94- Brand Guidelines (id: 01JEXAMPLE00001)
95- Marketing Images (id: 01JEXAMPLE00002)
96- Shoe Dog Highlights (id: 01JEXAMPLE00003)
97- Favorite Cocktails (id: 01JEXAMPLE00004)
98```
99 
100### Example 2: Getting knowledge for a topic
101 
102**Prompt:** "What are repeated lessons in my Shoe Dog highlights? Cite the original highlight in your answer."
103 
104The `list_topics` tool finds the topic, then `get_topic_knowledge` retrieves your saved highlights:
105 
106```
107### On Starting Out
108"I'd tell men and women in their midtwenties not to settle
109for a job or a profession or even a career. Seek a calling."
110---
111### On Selling
112"Don't tell people about your brand. Tell them about your
113belief. The ones who share it will find you."
114```
115 
116### Example 3: Using knowledge to make a decision
117 
118**Prompt:** "Here's a cocktail menu. Based on my saved favorites, what should I order?"
119 
120The `list_topics` tool finds Favorite Cocktails, then `get_topic_knowledge` retrieves your saved recipes and tasting notes. The AI cross-references the menu with your preferences to recommend a drink you'll actually like.
121 
122### Example 4: Combining multiple topics
123 
124**Prompt:** "Pull in my brand guidelines and marketing images. Help me design a new hero section with more of an Apple-style design approach."
125 
126The AI retrieves knowledge from both topics — your color palette, typography rules, tone of voice, and previous marketing visuals — then uses that context to generate a hero section concept that stays on-brand while incorporating the clean, minimal aesthetic you're going for.
127 
128## Development
129 
130```bash
131git clone https://github.com/obris-dev/obris-mcp.git
132cd obris-mcp
133uv sync
134```
135 
136To run locally via Claude Desktop, add to your `claude_desktop_config.json`:
137 
138```json
139{
140  "mcpServers": {
141    "obris": {
142      "command": "/full/path/to/uv",
143      "args": [
144        "--directory",
145        "/path/to/obris-mcp/src/obris_mcp",
146        "run",
147        "main.py"
148      ],
149      "env": {
150        "OBRIS_API_KEY": "$OBRIS_API_KEY"
151      }
152    }
153  }
154}
155```
156 
157> Run `which uv` to get the full path for `"command"`.
158 
159### Make commands
160 
161```bash
162make publish            # build and publish to PyPI
163make pack               # pack for MCP registry (runs version check first)
164make pack-and-publish   # pack, publish to PyPI, and publish to MCP registries
165make sync-version       # sync manifest.json and server.json to pyproject.toml version
166make check-version      # verify all version files match and compare to live server
167```
168 
169## Privacy Policy
170 
171This server sends your Obris API key to the Obris API (`api.obris.ai`) to authenticate requests. It retrieves topic and knowledge data from your account. The server itself does not store any data locally or send it to any third party, however your AI client may cache or retain retrieved content according to its own data policies.
172 
173For the full privacy policy, see [obris.ai/privacy](https://obris.ai/privacy).
174 
175## Support
176 
177For issues or questions, contact [support@obris.ai](mailto:support@obris.ai) or open an issue on [GitHub](https://github.com/obris-dev/obris-mcp/issues).
178 
179## License
180 
181MIT
182