RPCS-1 Agent Tuner & Translation Bridge MCP server
io.github.travisbergen2/rpcs1-agent-tunertravisbergen2streamable-httpv0.3.0Scanned
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
9 tools: 1 do something that can't be undone, 7 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the RPCS-1 Agent Tuner & Translation Bridge MCP server can do
The RPCS-1 Agent Tuner & Translation Bridge MCP server is published by the GitHub account travisbergen2. It has 9 tools. It can do things that cannot be undone, such as sending, paying or publishing (render_reply) and create or change data (7 tools: recommend_agent_configuration, interpret, fork, normalize and 3 more), but cannot delete data. 1 tool only reads.
1 tool can send data out of your system (render_reply).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 0.3.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
9 tools
Can't be undone 1Claude Code: ask
render_replyThe outbound half of the Translation Bridge loop.Can send data out1 finding
Why it is in this group
- The name "render_reply" says "reply": a word for sending, and what is sent cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe name "render_reply" says "reply": it sends or publishes something to other people.
Findings
- Warn
The server marks "render_reply" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "render_reply" says "reply": a word for sending, and what is sent cannot be taken back.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
Changes things 7Claude Code: ask
calibrate_profileBuild a ReceiverProfile (TI, SG, FT, UE, AR — continuous 0-100, never a category label) from five behavioral forced-choice answers.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
forkThe calibrated ambiguity surface: deterministic structural fork detectors (reference, scope, grouping, compare-vs-choose, polysemy) with character-offset spans, plus per-reading on…1 finding
Why it is in this group
- The name "fork" says "fork": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "fork" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "fork" says "fork": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
interpretDetect ambiguity in user messages using the RPCS-1 Signature Ambiguity Framework.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
normalizeClean up text with ellipses, fragments, and run-on thoughts into coherent prose.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Clean up text with ellipses, fragments, and run-on thoughts into coherent prose. Use when a user types stream-of-consciousness or fragmented input.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
prepare_promptThe inbound half of the Translation Bridge loop.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
recommend_agent_configurationDiagnose why a deployed AI agent may fail.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
route_intentEntropy routing over competing interpretations — the model proposes, the deterministic core disposes.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
Only reads 1Show 1 read-only tool
rewriteGet rewrite instructions for adapting text to a specific style: technical, plain, socially_gentle, concise, detailed, or direct.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get rewrite instructions for adapting text to a specific style: technical, plain, socially_gentle, concise, detailed, or direct. Use when communication needs tone adjustment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- idempotentHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:12 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 8
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://rpcs1.dev/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://rpcs1.dev
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 8 tools that change things (1 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://rpcs1.dev/mcp: tools/list returned 9 tools to an anonymous client, including render_reply (irreversible), recommend_agent_configuration (write), interpret (write), fork (write), normalize (write) and 3 more
Findings
Matches of fixed checks, with the text they matched.
- Warnfork
The server marks "fork" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "fork" says "fork": a word for a change.
- Warnrender_reply
The server marks "render_reply" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "render_reply" says "reply": a word for sending, and what is sent cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http rpcs1-agent-tuner https://rpcs1.dev/mcpclaude mcp add --transport http rpcs1-agent-tuner https://rpcs1.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__rpcs1-agent-tuner__rewrite"
],
"ask": [
"mcp__rpcs1-agent-tuner__recommend_agent_configuration",
"mcp__rpcs1-agent-tuner__interpret",
"mcp__rpcs1-agent-tuner__fork",
"mcp__rpcs1-agent-tuner__normalize",
"mcp__rpcs1-agent-tuner__calibrate_profile",
"mcp__rpcs1-agent-tuner__prepare_prompt",
"mcp__rpcs1-agent-tuner__render_reply",
"mcp__rpcs1-agent-tuner__route_intent"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as rpcs1-agent-tuner. Review it before you use it.
Capability tags behind 1 rule
- mcp__rpcs1-agent-tuner__render_reply outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.travisbergen2/rpcs1-agent-tuner/verify?hash=8ea1e5641cbd4d1b47193dbb94c29ca238b909a14a06eac6c10502efac785221" | jq -e '.changed == false'Pinned hash 8ea1e5641cbd, from Nov 20, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.travisbergen2/rpcs1-agent-tuner/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.travisbergen2/rpcs1-agent-tuner)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.
RPCS-1 Agent Tuner & Translation Bridge MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the RPCS-1 Agent Tuner & Translation Bridge MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 8 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the RPCS-1 Agent Tuner & Translation Bridge MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the RPCS-1 Agent Tuner & Translation Bridge MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: render_reply.
What tools does the RPCS-1 Agent Tuner & Translation Bridge MCP server have?
- 9 tools: 1 irreversible, 7 write, 1 read. render_reply, recommend_agent_configuration, interpret, fork, normalize, calibrate_profile, prepare_prompt, route_intent and 1 more.
Does the RPCS-1 Agent Tuner & Translation Bridge MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the RPCS-1 Agent Tuner & Translation Bridge MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): render_reply.
Has the RPCS-1 Agent Tuner & Translation Bridge MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.