ModelSpec MCP server
io.github.turbobeest/modelspecturbobeeststreamable-httpvb8da9336f3c5a0b56d47987251a29006a5b0487bScanned
Find AI models that fit a job from your requirements, sourced benchmarks and real cost.
9 tools: 7 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
7 tools here change things. Govern them.
- 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 ModelSpec MCP server can do
The ModelSpec MCP server is published by the GitHub account turbobeest. It has 9 tools. It can create or change data (7 tools: rank, model_info, policy_check, decide and 3 more), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding (long-description). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version b8da9336f3c5a0b56d47987251a29006a5b0487b.
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
Changes things 7Claude Code: ask
decideWhich models fit this job?1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The description is 3,225 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...teps for its candidates. Wrong: "Start with a/x", a shortlist, or a ranked table."
Description, as the server wrote it Which models fit this job? Call decide early. Returns answer, ranked results, may_qualify, reading and recovery hints, decision_id and snapshot. Never add a gate or constraint the user didn't state. Relax only constraints the user stated, one at a time, and say what was relaxed and why. Prefer the answer's own `relax` suggestions. A tie stays a tie. Don't promote a member by knowledge from outside the response. Cite only evidence in the response. Never add benchmark figures from memory. Tied or partial answer: report the tie and caveats, pick no member; a null answer names no pick and says what's missing. A null cost is unknown. Never show it as $0.00 or "free". One vocabulary lookup per unknown facet, then decide. Read `next` before another call. Size `task_tokens` from the user's own task, and say what you assumed. Don't copy the guide's example sizes. Template weights are examples, not requirements. If the evidence basis or board does not match the task, say so: Arena web-dev evidence does not establish chat quality. p_best is the probability of ranking best under the Spec and evidence uncertainty, not the probability of matching the user's task or satisfying its requirements. Read reading when present. Present answer.kind=tied among all answer.members, including with_estate; tie-breakers are conditional. State requirements in reading.not_applied or error.issues that were not applied, including requirements removed after a rejected call. A retry does not verify them. Report estimates as estimates: fits_hardware membership is not measured fit for a specific quantization and context workload. Follow reading.do_not_claim. Never claim a rank the response does not show. Present `summary_for_user` to the user unchanged and keep every `must_mention` item. When `next_move` is present, offer it instead of a pick. Needs an API key (Authorization: Bearer). Costs 1 or 2 credits a call; $0.0053–$0.02 per credit by plan or pack (https://modelspec.dev/pricing/). Not a router: call once per job or role, not per request; route among its chosen models. Proxies POST https://api.modelspec.dev/v1/decide. MCP decide returns a bounded answer of at most 16 KB, summary included. Drill down with evidence_for. Complete rows need fields:null; explanation.fetch names what was removed and how to fetch it. With explain unset or "none": explain=none, limit=10, fields=model_rank,cost_per_task,estimates,p_best. summary/full adds contributions and evidence. omitted counts removed records; explain=none skips eliminations. Explicit fields, including null, pass through. Oversize responses use a trimmed notice with explanation.fetch. decision_id is a citation, not a stored lookup. task free text is rejected; where is an array. Examples, recovery and budgets: https://modelspec.dev/agents.md. Null means unresearched or unpublished, never a guess. Sourced card values include a URL and read date. Returns the origin JSON and URL without invented fields. Example. Answer: status partial, answer.kind tied (a/x, b/y), next_move.kind decide_by_testing. Right report: summary_for_user verbatim, each must_mention item, then next_move.steps for its candidates. Wrong: "Start with a/x", a shortlist, or a ranked table.
feedbackWas an answer reliable?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.
Description, as the server wrote it Was an answer reliable? Returns recorded/not_recorded for a rating after acting; include decision_id. Free, no key, and no Authorization header is forwarded. No prompts, keys or personal details in note; no questions or support. Storage stays off until covered by the privacy statement. Proxies POST https://api.modelspec.dev/v1/feedback.
hardware_fitDoes this workload fit?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.
Description, as the server wrote it Does this workload fit? Returns measured for an exact cited run, estimated with sources, or undetermined. Uses basis full with sourced headroom, or basis lower_bound for unlikely only. Missing headroom cannot establish likely. Estimates never prove fit. Memory is decimal GB per device, never pooled. Needs an API key (Authorization: Bearer). Costs 2 credits a call; $0.0053–$0.02 per credit by plan or pack (https://modelspec.dev/pricing/). It doesn't choose a model. Proxies POST https://api.modelspec.dev/v1/hardware-fit.
model_infoWhat does one model's card say?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.
Description, as the server wrote it What does one model's card say? Reads https://modelspec.dev/api/models/<model_id>.json. Split mode returns only its display name. Needs an API key. Not current evidence or a ranking; use decide.
policy_checkWhich models and platforms does my policy allow?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.
Description, as the server wrote it Which models and platforms does my policy allow? Returns pass, fail or undetermined per model/platform for licence, origin and data handling; undetermined is not a pass. Needs an API key (Authorization: Bearer). Costs 5 credits a call; $0.0053–$0.02 per credit by plan or pack (https://modelspec.dev/pricing/). It doesn't choose a model; use decide among passing rows. Proxies POST https://api.modelspec.dev/v1/policy-check with these arguments and Authorization.
rankLegacy v1; use decide.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.
Description, as the server wrote it Legacy v1; use decide. Deprecated fixed-benchmark ranking; scores lag the catalogue and newer models may be unranked. Which models lead a fixed use-case profile? Returns a shortlist with evidence_basis and input provenance, not a quality verdict. Needs an API key (Authorization: Bearer). Costs 1 credit a call; $0.0053–$0.02 per credit by plan or pack (https://modelspec.dev/pricing/). Don't call it as a fallback when decide has no single leader; report its tie. Present `summary_for_user` to the user unchanged and keep every `must_mention` item. When `next_move` is present, offer it instead of a pick. Proxies POST https://api.modelspec.dev/v1/rank with these arguments.
vocabWhat can a Spec say?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.
Description, as the server wrote it What can a Spec say? Returns ids and task types. Needs an API key. One vocabulary lookup per unknown facet, then decide. Use decide to compare models. Starter includes a minimal Spec. Compact pages: at most 20 rows, no counts; empty pages end results. Search ranks all tokens before subsets; misses offer nearest ids. Split-mode full details exclude model facts and counts.
Only reads 2Show 2 read-only tools
compare_modelsWhat facts do 2 to 4 named models have?No findings
Why it is in this group
- The name "compare_models" says "compare": a word for reading.
Description, as the server wrote it What facts do 2 to 4 named models have? Returns sourced snapshot facts, offerings and evidence in caller order; unknowns stay null. Needs an API key (Authorization: Bearer). Costs 2 credits a call; $0.0053–$0.02 per credit by plan or pack (https://modelspec.dev/pricing/). It doesn't choose a model and does not rank. Proxies POST https://api.modelspec.dev/v1/compare-models with {models: [...]} at most 16 KB.
list_use_casesWhich legacy profiles and ranking rules exist?No findings
Why it is in this group
- The name "list_use_cases" says "list": a word for reading.
Description, as the server wrote it Which legacy profiles and ranking rules exist? Returns https://modelspec.dev/api/rank/profiles.json with evidence floors and the neutrality commitment. Needs an API key. Use decide for decisions.
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 or outbound.
- 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 out0
- 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
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.modelspec.dev/mcp: tools/list returned 9 tools to an anonymous client, including rank (write), model_info (write), policy_check (write), decide (write), hardware_fit (write) and 2 more
Findings
Matches of fixed checks, with the text they matched.
- Infodecide
The description is 3,225 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...teps for its candidates. Wrong: "Start with a/x", a shortlist, or a ranked table."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:policy_checkChanges thingsinputSchema
- Changed:rankChanges thingsinputSchema
Install
Pinned to version b8da9336f3c5a0b56d47987251a29006a5b0487b. Values in angle brackets are yours to fill in.
claude mcp add --transport http modelspec https://api.modelspec.dev/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http modelspec https://api.modelspec.dev/mcp --header 'Authorization: <your-authorization>'Run 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__modelspec__list_use_cases",
"mcp__modelspec__compare_models"
],
"ask": [
"mcp__modelspec__rank",
"mcp__modelspec__model_info",
"mcp__modelspec__policy_check",
"mcp__modelspec__decide",
"mcp__modelspec__hardware_fit",
"mcp__modelspec__vocab",
"mcp__modelspec__feedback"
],
"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 modelspec. Review it before you use it.
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.turbobeest/modelspec/verify?hash=1bcfa74cfc6515e8fcf65785ed922b0b95068984130072de27ebe133ae29c461" | jq -e '.changed == false'Pinned hash 1bcfa74cfc65, from Nov 20, 2026, 16:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.turbobeest/modelspec/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.turbobeest/modelspec)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.
ModelSpec MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ModelSpec MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 7 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ModelSpec MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ModelSpec MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the ModelSpec MCP server have?
- 9 tools: 7 write, 2 read. rank, model_info, policy_check, decide, hardware_fit, vocab, feedback, list_use_cases and 1 more.
Does the ModelSpec MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ModelSpec MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ModelSpec MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.