Skip to content
RPCS-1 Agent Tuner logo

RPCS-1 Agent Tuner MCP server

Which MCP servers are RPCS-1 Agent Tuner's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-11

← Back to RPCS-1 Agent Tuner

Whose server it is
  • Addresshttps://rpcs1.dev/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on rpcs1.dev when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools9
  • Server calls itselfrpcs1-agent-tuner
  • Server version0.4.2
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 357 ms.

Should an agent connect itNot proven either way yet
  • Its tools do Check how your message reads before sending it, but not Connect your notes as memory inside Claude and other AI apps.
  • Checked on 6 of the 7 days it takes to judge reliability.

Once connected

  • For "Check how your message reads before sending it", the likely first call is render_reply.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 6, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it1 of 2 use cases
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer209 ms
  • Space in an agent's context≈ 3,478 tokensthe definitions of all its tools (9), which an agent carries on every turn
  • Tool definitionsA · 98 of 100
  • Typed results1 of 9 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 9

What an agent can do with it

  • can do · Check how your message reads before sending it
  • not sure · See what text leaves your machine to AI systems
  • cannot · Connect your notes as memory inside Claude and other AI apps

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers9 tools · read 2026-10-28
  • 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…

  • 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…

  • 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…

  • 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.

  • 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.

  • 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…

  • 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…

  • 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…

  • 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…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "rpcs1": {
      "type": "http",
      "url": "https://rpcs1.dev/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http rpcs1 https://rpcs1.dev/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://rpcs1.dev/mcp as a custom connector in the settings.

OpenAPI spec

1 paths, read 2026-10-11. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.