Connect Hermes to Rafter’s MCP server
Hermes takes hosted MCP servers as a first-class transport — no bridge needed. A few lines of YAML and it can search your team's shared memory, skills and agents.
Add Rafter to config.yaml
Add this to
~/.hermes/config.yaml. The key ismcp_serverswith an underscore — not the camel-case spelling most other clients use.mcp_servers: rafter: url: "https://app.heyrafter.xyz/api/mcp" auth: oauthauth: oauth is what tells Hermes to run the OAuth 2.1 PKCE flow rather than expect a token.
Reload and sign in
Run
/reload-mcpin Hermes to pick up the change. On the first connect a browser window opens for authorization — sign in and pick the workspace to connect.Tokens persist to ~/.hermes/mcp-tokens/rafter.json and refresh across sessions.
Ask something your team already knows
Try “Search Rafter for our onboarding steps and follow them.”
Your first five minutes
The connection is the easy part. The habit is what pays: make Hermes check the shared brain before it improvises. Three things to try in Hermes:
- “What do we know about [a client or project]?”Rafter’s search answers from your team’s actual notes — with what they cite.
- “How do we [something a teammate has done before]? Follow the skill if we have one.”Skills are the team’s way of doing it, taught once and reused.
- “Save this as a memory: [a decision you just made].”Written back with add_memory — versioned, searchable, there for the next person.
To make it automatic, paste this line into Hermes’s project or system instructions:
Check Rafter first: search our skills and memories before you answer, and save anything durable back with add_memory.
A longer startup prompt and a ready-made Claude Code skill live in the rafter-mcp repo.
Troubleshooting
Do I need mcp-remote or another bridge?
No. Hermes treats hosted HTTP servers as a first-class transport alongside stdio, so Rafter connects directly.
Which workspace should I pick when signing in?
The one whose skills and memories you want this tool to see. A connection sees exactly what you can see — your teams and your role — never more. You can connect again later and grant a different workspace.
Is my team's content used to train AI models?
No. Rafter does not use your content to train generalized or foundation models — see the privacy policy.
Give your whole team the same brain.From $29 per user — see pricing.
Create your account