RPCS-1 Agent Tuner & Translation Bridge
Server Details
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- travisbergen2/rpcs1-sdk
- GitHub Stars
- 0
- Server Listing
- RPCS-1 Agent Tuner & Translation Bridge
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 9 tools
Tools like interpret, fork, prepare_prompt, and route_intent all touch ambiguity handling, but each has a clearly delineated role (span-level detection, AR-level assessment, inbound translation, commit-vs-clarify authority). Minor overlap exists but descriptions prevent misselection.
All tool names follow a consistent snake_case verb_noun pattern (calibrate_profile, prepare_prompt, render_reply) with only 'fork' as a single verb, still matching the verb-first style. No mixing of conventions.
9 tools is well-scoped for a server covering both profile calibration and translation bridging. Each tool serves a distinct function without redundancy or bloat.
The surface covers the full lifecycle: profile creation (calibrate_profile), agent diagnosis (recommend_agent_configuration), inbound processing (prepare_prompt), routing decisions (route_intent), ambiguity detection (interpret, fork), outbound rendering (render_reply), and style adaptation (rewrite, normalize). No obvious gaps.
Available Tools
9 toolscalibrate_profileCalibrate a user’s receiver profileARead-onlyIdempotentInspect
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 primitive) to get the profile. Store the returned profile JSON in the user’s notes or memory and pass it to render_reply / prepare_prompt on every turn. Deterministic and stateless — nothing is stored server-side. Schema: https://rpcs1.dev/v1/receiver-profile.json
Inputs: answers.
forkFork view — how could this message read?ARead-onlyIdempotentInspect
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. Returns competing readings, an ask-back question, and a forked-answer scaffold. Silent on clean text by contract. Runs the deterministic mirror floor only over MCP (no model). Prefer this over interpret for span-level ambiguity detection: interpret’s entity list is a word-list engine (calibrated 2026-08-15: no discrimination on conversational text) — advisory only.
Inputs: text (required), rejected.
interpretInterpret ambiguous human inputARead-onlyIdempotentInspect
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 vague, passive-aggressive, or underspecified.
Inputs: text (required), risk.
normalizeNormalize fragmented human inputARead-onlyIdempotentInspect
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 (required).
prepare_promptPrepare a user’s message before acting on itARead-onlyIdempotentInspect
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 level, and — profile-aware — whether to clarify or commit. Call this before acting on any ambiguous user request. Scope note: its detectors are lexical/structural (vague signals, ambiguous references) — for the commit-vs-clarify DECISION, route_intent (with your own proposed readings) is the authority; when they disagree, follow route_intent.
Inputs: text (required), risk, profile.
recommend_agent_configurationRecommend AI agent configurationARead-onlyIdempotentInspect
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, strategy), regime prediction, reasoning, and warnings. Optionally pass target_model (the actual model id) to attach MEASURED per-model receiver posture (E-LIT table): evidence-graded literalness, truth-override boundary, and translation directives. Deterministic, stateless, read-only — does not store past recommendations.
Inputs: task, environment, target_model, target_platform. Returns: warnings, reasoning, confidence, predicted_regime, +3 more
render_replyRender a reply for a specific user’s receiver profileARead-onlyIdempotentInspect
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 why-trace). Apply the instructions to your draft before answering. Call this on every reply to a calibrated user.
Inputs: text (required), profile (required).
rewriteRewrite text for a target audienceARead-onlyIdempotentInspect
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 (required), style.
route_intentRoute an ambiguous request: commit, present options, or clarifyARead-onlyIdempotentInspect
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-typo readings, idiom-vs-literal readings, and domain senses) and pass them as hypotheses, ideally with your own likelihoods (0–1 per reading) AND a paraphrase per reading — the user’s message rewritten unambiguously under that interpretation, so the user can VERIFY intent by recognition before anything commits (one misread prompt skews a whole thread). The router computes the posterior and its normalized entropy T̂ and returns the decision: commit (one reading dominates), commit_with_note (close alternative disclosed), present_options (several readings live), or clarify (ask before acting — open-endedly when nothing discriminates). Thresholds adapt to the user’s ReceiverProfile (AR widens/narrows the commit region; high FT discloses near-ties). This tool is the commit-vs-clarify AUTHORITY in the pipeline. Omitting hypotheses falls back to a generic six-intent PRODUCT-ROUTING starter set — do not use the fallback for interpreting arbitrary sentences. Deterministic, stateless, read-only. Benchmarked: RTEB v1.1 (developer-bench grade; see docs/routing.md).
Inputs: text (required), profile, hypotheses, likelihoods.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Scan an AI agent's instructions and tools for behavior risks and generate probes that test them.
Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.
Diagnose AI workflows for failure, security, and handoff risks — RED/AMBER/GREEN per node.
Preflight QA for AI-agent deliverables with structured verdicts and repair guidance.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceFind the step that caused an AI agent’s failure. Ask your assistant why a run failed, see the evidence, and check whether a suggested fix works.17Apache 2.0
- AlicenseBqualityDmaintenanceAutomatically analyzes and optimizes AI prompts by calculating clarity scores, detecting risks, asking clarifying questions, and adding domain-specific requirements to improve AI interaction quality.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to test load-bearing assumptions through an evidence-driven pipeline, detect sycophancy and causal errors, calibrate confidence, and route decisions to act, revise, or halt.28 PyPIMIT
- AlicenseAqualityBmaintenanceZero-dependency token optimizer, test-failure triage gate, and System 1.5 semantic guardrail for AI coding agents. Intercepts compiler errors, missing dependencies, and doom loops in < 500µs.612MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.