hermes-mcp-bridge
A zero-friction stdio MCP bridge connecting Cursor Desktop to a local Hermes Agent, enabling natural language task delegation with session continuity and profile awareness.
README
<p align="center"> <img src="https://img.shields.io/badge/Python-3.11%2B-blue" alt="Python"> <img src="https://img.shields.io/badge/transport-stdio-green" alt="stdio"> <img src="https://img.shields.io/badge/deps-mcp%20%7C%20httpx%20%7C%20pydantic-lightgrey" alt="deps"> <img src="https://img.shields.io/badge/license-Apache--2.0-yellow" alt="license"> </p>
hermes-mcp-bridge
A zero-friction stdio MCP bridge connecting Cursor Desktop to a local Hermes Agent — no OAuth, no tunnels, no Dynamic Client Registration.
1. Architecture
Cursor Desktop hermes-mcp-bridge Hermes Gateway
┌──────────────┐ stdio ┌─────────────────────┐ HTTP ┌──────────────┐
│ mcp.json │ ─────────→ │ FastMCP │ ───────→ │ 127.0.0.1 │
│ command: │ │ ├ hermes_ask() │ Bearer │ :8642 │
│ /home/... │ ←───────── │ ├ hermes_check() │ ←─────── │ /v1/chat/ │
└──────────────┘ stdio │ ├ hermes_cancel() │ JSON │ completions │
│ └ hermes_reset() │ └──────────────┘
└─────────────────────┘
X-Hermes-Session-Id → REPL context
1.1 Comparison with mlennie/hermes-mcp
mlennie/hermes-mcp |
hermes-mcp-bridge |
|
|---|---|---|
| Transport | Streamable HTTP | stdio |
| Auth | OAuth 2.1 + DCR | Bearer header |
| External deps | cloudflared / ngrok | none |
| Process model | Standalone daemon | Cursor subprocess |
| Deployment files | 5 configs + systemd unit | 2 files |
2. Profile Awareness
The bridge connects to the same Hermes profile your gateway is serving. It inherits everything that profile has loaded — skills, memory, tools, sessions.
You can pick which profile to use in two ways:
| Method | What you do | When to use |
|---|---|---|
| Set a default | Edit ~/.config/hermes-mcp-bridge/config.toml |
You mostly use one profile |
| Mention it in chat | Say "Use Hermes with the default profile to…" in the Cursor chat input | You switch profiles often |
Neither requires touching mcp.json or restarting Cursor.
2.1 Default profile (config.toml)
# ~/.config/hermes-mcp-bridge/config.toml
model = "general_researcher" # ← used when no profile arg is passed
2.2 Switching profiles from Cursor
The hermes_ask tool exposes an optional profile parameter. Just mention
which profile you want — Cursor's LLM reads the tool signature and passes it.
┌─────────────────────────────────────────────────────────┐
│ You say in Cursor │
├─────────────────────────────────────────────────────────┤
│ "Use Hermes with the default profile to send an email" │
│ → hermes_ask(prompt="send an email", │
│ profile="default") │
│ │
│ "Ask Hermes to search arXiv for MCP papers" │
│ → hermes_ask(prompt="search arXiv...") │
│ # no profile → uses config.toml default │
└─────────────────────────────────────────────────────────┘
No mcp.json changes, no config edits, no restart. Just say the profile name.
2.3 Discover available profiles
curl -s http://127.0.0.1:8642/v1/models \
-H "Authorization: Bearer change...-dev"
# → {"data": [{"id": "general_researcher", ...}, {"id": "default", ...}]}
If your gateway only runs one profile, only one
idappears. Start additional gateway instances on different ports to serve multiple profiles simultaneously.
3. Why This Exists
mlennie/hermes-mcp v0.4.0 hits three real-world blockers:
- OAuth 2.1 demands an HTTPS tunnel — even when Cursor and Hermes run on the same machine.
- No Dynamic Client Registration support —
mcp-remotecrashes withIncompatible auth server. - Cursor's localhost OAuth callback is broken — its built-in MCP HTTP client returns
ERR_EMPTY_RESPONSEonlocalhost.
This bridge drops the HTTP transport layer entirely, runs as a stdio subprocess, and sidesteps all three.
4. Quick Start
4.1 Install
git clone https://github.com/<your-org>/hermes-mcp-bridge.git
cd hermes-mcp-bridge
uv tool install --editable .
4.2 Configure
mkdir -p ~/.config/hermes-mcp-bridge
cat > ~/.config/hermes-mcp-bridge/config.toml << 'EOF'
api_url = "http://127.0.0.1:8642"
api_key = "change-me-local-dev" # must match API_SERVER_KEY in ~/.hermes/.env
model = "general_researcher"
timeout_seconds = 300
EOF
chmod 600 ~/.config/hermes-mcp-bridge/config.toml
4.3 Register with Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"hermes": {
"command": "/home/nirvana/.local/bin/hermes-mcp-bridge"
}
}
}
4.4 Restart Cursor
Settings → MCP → hermes should show connected.
5. Tools
| Tool | Signature | Purpose |
|---|---|---|
hermes_ask |
(prompt, session_id?, profile?) → str |
Delegate a task to Hermes Agent |
hermes_check |
(job_id) → str |
Poll async job status (stub) |
hermes_cancel |
(job_id) → str |
Cancel an async job (stub) |
hermes_reset |
() → str |
Clear the job queue (stub) |
The last three are kept for API parity.
hermes-mcp-bridgeruns synchronously —hermes_askblocks until the full Agent response is ready.
6. REPL Context (Session Continuity)
Hermes remembers what you told it earlier — just keep talking in the same
Cursor chat. Cursor automatically reuses the same session_id across turns.
┌─────────────────────────────────────────────────────────┐
│ You say in Cursor │
├─────────────────────────────────────────────────────────┤
│ "Use Hermes to remember that my lucky number is 42" │
│ → Hermes remembers 42 │
│ │
│ "Ask Hermes what my lucky number is" │
│ → Hermes answers 42 │
│ (same session_id — context preserved) │
└─────────────────────────────────────────────────────────┘
The bridge passes session_id through as the X-Hermes-Session-Id HTTP header.
The gateway uses it to maintain context across calls.
No special syntax. No session IDs to track. Just talk normally — Hermes remembers.
7. Configuration Reference
~/.config/hermes-mcp-bridge/config.toml
| Key | Default | Description |
|---|---|---|
api_url |
http://127.0.0.1:8642 |
Hermes Gateway HTTP API address |
api_key |
— | Must match API_SERVER_KEY in ~/.hermes/.env |
model |
general_researcher |
Must match a model ID from gateway /v1/models |
timeout_seconds |
300 |
Max wait per hermes_ask call |
Environment variable overrides (higher priority): HERMES_BRIDGE_API_URL, HERMES_BRIDGE_API_KEY.
8. Security
- All network traffic is confined to the
127.0.0.1loopback interface. - The API key lives in
~/.config/hermes-mcp-bridge/config.toml(mode600). - The repository itself contains no keys, secrets, or credentials.
- Cursor spawns the bridge via stdio — no ports are exposed.
9. License
Apache-2.0
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。