RPCS-1 Agent Tuner & Translation Bridge is an MCP server with 9 tools an agent can call, among them calibrate_profile, fork, interpret. It answers at https://rpcs1.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
calibrate_profile | Build a ReceiverProfile (TI, SG, FT, UE, AR — continuous 0-100, never a category label) from five behavioral forced-choice answers. Call with NO answers to get the five questions to ask the user; call again with their answers (a/b/c per pri Inputs: answers |
fork | The calibrated ambiguity surface: deterministic structural fork detectors (reference, scope, grouping, compare-vs-choose, polysemy) with character-offset spans, plus per-reading one-line clarifiers the sender can append to lock a reading in Inputs: text, rejected |
interpret | Detect ambiguity in user messages using the RPCS-1 Signature Ambiguity Framework. Returns AR level (AR0-AR5), confidence, candidate interpretations with scores, clarifying questions, and suggested next step. Use when a user says something v Inputs: text, risk |
normalize | Clean up text with ellipses, fragments, and run-on thoughts into coherent prose. Use when a user types stream-of-consciousness or fragmented input. Inputs: text |
prepare_prompt | The inbound half of the Translation Bridge loop. Takes the user’s raw message (possibly ambiguous, fragmented, or underspecified) plus their ReceiverProfile, and returns the recovered intent, a canonical translation to act on, ambiguity lev Inputs: text, risk, profile |
recommend_agent_configuration | Diagnose why a deployed AI agent may fail. Takes environmental entropy, predictability, stakes, context horizon, and commitment style, then returns receiver profile values (TI, SG, FT, UE, AR), platform parameters (temperature, top_p, strat Inputs: task, environment, target_platform, target_model |
render_reply | The outbound half of the Translation Bridge loop. Takes your draft reply plus the user’s ReceiverProfile and returns deterministic rendering instructions (structure, warmth, explicitness, revision posture, ambiguity handling — each with a w Inputs: text, profile |
rewrite | Get rewrite instructions for adapting text to a specific style: technical, plain, socially_gentle, concise, detailed, or direct. Use when communication needs tone adjustment. Inputs: text, style |
route_intent | Entropy routing over competing interpretations — the model proposes, the deterministic core disposes. YOU generate the candidate readings of the user’s message (3–7 short hypotheses covering the plausible interpretations, INCLUDING likely-t Inputs: text, hypotheses, likelihoods, profile |
Every block below points at https://rpcs1.dev/mcp. Pick your client and copy.
claude mcp add --transport http rpcs-1-agent-tuner-translation-b https://rpcs1.dev/mcp
{
"mcpServers": {
"rpcs-1-agent-tuner-translation-b": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://rpcs1.dev/mcp"]
}
}
}{
"mcpServers": {
"rpcs-1-agent-tuner-translation-b": {
"url": "https://rpcs1.dev/mcp"
}
}
}{
"servers": {
"rpcs-1-agent-tuner-translation-b": {
"type": "http",
"url": "https://rpcs1.dev/mcp"
}
}
}{
"context_servers": {
"rpcs-1-agent-tuner-translation-b": {
"url": "https://rpcs1.dev/mcp"
}
}
}{
"mcpServers": {
"rpcs-1-agent-tuner-translation-b": {
"serverUrl": "https://rpcs1.dev/mcp"
}
}
}{
"mcpServers": {
"rpcs-1-agent-tuner-translation-b": {
"url": "https://rpcs1.dev/mcp"
}
}
}name: RPCS-1 Agent Tuner & Translation Bridge
version: 0.0.1
schema: v1
mcpServers:
- name: RPCS-1 Agent Tuner & Translation Bridge
type: streamable-http
url: https://rpcs1.dev/mcp{
"mcpServers": {
"rpcs-1-agent-tuner-translation-b": {
"httpUrl": "https://rpcs1.dev/mcp"
}
}
}{
"mcpServers": {
"rpcs-1-agent-tuner-translation-b": {
"type": "http",
"url": "https://rpcs1.dev/mcp"
}
}
}{
"mcpServers": {
"rpcs-1-agent-tuner-translation-b": {
"url": "https://rpcs1.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Frpcs1.dev%2Fmcp&type=streamable_http&id=rpcs-1-agent-tuner-translation-b&name=RPCS-1%20Agent%20Tuner%20%26%20Translation%20Bridge
It answered our last check on 24 October 2026 in 226 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
9, as returned by the server's own tools/list on 22 September 2026: calibrate_profile, fork, interpret, normalize, prepare_prompt, recommend_agent_configuration, render_reply, rewrite, and 1 more.
It answered our last check on 24 October 2026 in 226 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://rpcs1.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.travisbergen2. Endpoint host: rpcs1.dev. ARD identifier: urn:air:io.github.travisbergen2:mcp:rpcs1-agent-tuner.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.