RPCS-1 Agent Tuner & Translation Bridge
RPCS-1 turns an agent's operating conditions into derived runtime settings (temperature, context strategy, failure-mode read), and its Translation Bridge…
What it can do
- Recommend Agent Configuration: Diagnose why a deployed AI agent may fail. Returns suggested runtime parameters, a context strategy, a predicted regime, reasoning, warnings, and a next test. Determinis
- Interpret: Detect ambiguity in user messages. Returns AR level, confidence, candidate interpretations, clarifying questions, and a suggested next step.
- Normalize: Clean up fragmented human input with ellipses and run-on thoughts into coherent prose.
What data it sees
Do you need an account
No: the server works without sign-in
RPCS-1 turns an agent's operating conditions into derived runtime settings (temperature, context strategy, failure-mode read), and its Translation Bridge calibrates a per-user receiver profile so every reply is rendered for that user's communication style. 7 tools, no API key.
How to connect
How to connect RPCS-1 Agent Tuner & Translation Bridge to Claude
The server address to paste into Claude settings:
https://rpcs1-agent-tuner--travisbergen2.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect RPCS-1 Agent Tuner & Translation Bridge to ChatGPT
The server address to paste into ChatGPT settings:
https://rpcs1-agent-tuner--travisbergen2.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect RPCS-1 Agent Tuner & Translation Bridge to Cursor
The server address to paste into Cursor settings:
https://rpcs1-agent-tuner--travisbergen2.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (7)
Raw names from tools/list. Only developers need these.
| recommend_agent_configuration | Diagnose why a deployed AI agent may fail. Returns suggested runtime parameters, a context strategy, a predicted regime, reasoning, warnings, and a next test. Deterministic, stateless, and read-only. Optionally pass target_model to attach measured per-model receiver posture (evidence-graded). |
| interpret | Detect ambiguity in user messages. Returns AR level, confidence, candidate interpretations, clarifying questions, and a suggested next step. |
| normalize | Clean up fragmented human input with ellipses and run-on thoughts into coherent prose. |
| rewrite | Return style-specific rewrite instructions for technical, plain, socially gentle, concise, detailed, or direct communication. |
| calibrate_profile | Build a continuous communication-preference profile from five behavioral forced-choice answers. Omit answers to receive the questions. The profile is not a diagnosis or category label, and nothing is stored server-side. |
| prepare_prompt | Recover likely intent from a raw message before acting. Returns a canonical translation, ambiguity level, and whether to clarify or commit; an optional receiver profile shapes that choice. |
| render_reply | Return deterministic rendering instructions for a draft reply and a receiver profile. Apply the returned structure, warmth, explicitness, revision, and ambiguity guidance before answering. |