MCP.Market

ModelSpec MCP server

online · 100% uptime
by turbobeest·io.github.turbobeest/modelspec·vb8da9336f3c5a0b56d47987251a29006a5b0487b·2 stars
No reviews yet

Find AI models that fit a job from your requirements, sourced benchmarks and real cost.

A85/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

2 stars

Reviews

Write one

Nobody has reviewed ModelSpec yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

ModelSpec tools (8)

write = sends, deletes, buys or posts
  • compare_modelsFree

    Which facts, offerings and evidence do 2 to 4 named models have? Returns snapshot facts, offerings, evidence and sources in caller order; unknown values stay null. Needs an API key (Authorization: Bearer). Costs 2 credits a call; a credit costs $0.0053–$0.02 depending on the plan or pack (https://modelspec.dev/pricing/). It doesn't choose a model and does not rank or choose a winner. Proxies POST https://api.modelspec.dev/v1/compare-models with {models: [...]} and returns at most 16 KB.

  • decideFree

    Which models fit this job? 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; a credit costs $0.0053–$0.02 depending on the plan or pack (https://modelspec.dev/pricing/). Not a router: call it once per job or role, not per request, then route among the models it recommends. Proxies POST https://api.modelspec.dev/v1/decide. Call decide early with a template-based Spec; refine from reading and recovery hints. Put Musts in where: these gates exclude. Put Prefers in optimize.weights: weights rank and never exclude. Unknown values go to may_qualify. Pin snapshot for reproducibility. 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 or full also sends contributions and evidence. omitted counts removed records; explain=none does not compute eliminations. explicit fields, including null, is sent as given. Over 16 KB the body is a trimmed notice and explanation.fetch says how to resend. decision_id is a citation, not a stored lookup. task free text is rejected; where is an array. Call shape, examples, recovery and budgets: https://modelspec.dev/agents.md. Null means not researched or not published, never a guess. Every sourced value on a card carries a URL and a read date. This tool returns the origin's JSON plus the origin URL; it does not invent 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.

  • feedbackFree

    Was a ModelSpec answer reliable? After you act on an answer, say whether it was reliable, unreliable, trustworthy, untrustworthy or confusing, by proxying POST https://api.modelspec.dev/v1/feedback. Include the answer's decision_id. Free, no key, and no Authorization header is forwarded. Not for questions or support. Never put a prompt, a key or personal details in note. The response says status "recorded" or "not_recorded" (storage is off until the privacy statement covers it).

  • list_use_casesFree

    Which ranking profiles exist, and what is the ranking policy? Returns https://modelspec.dev/api/rank/profiles.json: the profiles, the evidence floors and the neutrality commitment. Needs an API key. Not a decision: use decide for that.

  • model_infoFree

    What does ModelSpec's card say about one model? Reads https://modelspec.dev/api/models/<model_id>.json (model_id is provider/slug). With data splitting, returns only the model's display name from the Worker vocabulary. Needs an API key. Not current evidence and not a ranking: use decide for that.

  • policy_checkFree

    Which models, on which platforms, does my policy allow? Checks a policy document (licence, origin, data handling) per model and per platform. Returns pass, fail or undetermined for each row; undetermined is not a pass. Needs an API key (Authorization: Bearer). Costs 5 credits a call; a credit costs $0.0053–$0.02 depending on the plan or pack (https://modelspec.dev/pricing/). It doesn't choose a model: use decide to choose among the ones that pass. Proxies POST https://api.modelspec.dev/v1/policy-check with this tool's arguments as the JSON body; Authorization is forwarded.

  • rankFree

    Legacy v1; use decide. Deprecated: the retired fixed-benchmark ranking, whose scores lag the catalogue; newer models are often unranked. Which models rank highest for one fixed use-case profile? Returns a shortlist with evidence_basis, input provenance, not a quality verdict. Needs an API key (Authorization: Bearer). Costs 1 credit a call; a credit costs $0.0053–$0.02 depending on the plan or pack (https://modelspec.dev/pricing/). Don't call it as a fallback when decide names no single leader: report decide's 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 this tool's arguments as the JSON body.

  • vocabFree

    What can a decide spec say? Returns the decision vocabulary: valid facet ids, benchmarks, domains, providers and task types. Compact by default, with 20 rows per page and no counts. Split-mode full details exclude per-model facts and counts. Needs an API key. Use it for missing ids, not to compare models. One vocabulary lookup per unknown facet, then decide. Read `next` before another call. section=starter returns a ready-to-send minimal Spec and a next hint. Search covers every section's ids, labels, definitions, values and synonyms. All tokens rank first; a content-token subset can match. A miss returns the nearest ids. An explicit non-starter section scopes the search. Use id or ids for row details, or detail=full for all display details. Use offset and limit to page matches across sections, including full details; an empty page ends the list.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

1 low
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 615ms20/20
  • Tool poisoning8 tool descriptions checked13/15
  • Auth qualityAPI key sent as a header8/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • lowUnusually long tool description (over 2,000 characters)poison.long-description
    tool decide: …Which models fit this job? 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; a credit costs $0.0053–$0.02 depending on the plan or pack (https://modelspec.dev/pricing/). Not a router: call it once per job or role, not per request, then route among the models it recommends. Proxies POST https://api.modelspec.dev/v1/decide. Call decide early with a template-based Spec; refine from reading and recovery hints. Put Musts in where: these gates exclude. Put Prefers in optimize.weights: weights rank and never exclude. Unknown values go to may_qualify. Pin snapshot for reproducibility. 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 or full also sends contributions and evidence. omitted counts removed records; explain=none does not compute eliminations. explicit fields, including null, is sent as given. Over 16 KB the body is a trimmed notice and explanation.fetch says how to resend. decision_id is a citation, not a stored lookup. task free text is rejected; where is an array. Call shape, examples, recovery and budgets: https://modelspec.dev/agents.md. Null means not researched or not published, never a guess. Every sourced value on a card carries a URL and a read date. This tool returns the origin's JSON plus the origin URL; it does not invent 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.…
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How ModelSpec compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 70% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
304 ms
faster than 47% of 30,031 servers
GitHub stars
2
more than 75% of 28,688 servers

What its tools let an agent do: 8 read

Install ModelSpec in Claude Code, Cursor or VS Code

claude mcp add --transport http modelspec https://api.modelspec.dev/mcp
Add to Cursor

What the publisher says

From the ModelSpec repository's README, as published. We do not edit it. Read it on GitHub

ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work. It reads a spec, filters models and offerings against its constraints, and explains the decision from a versioned snapshot. The catalogue starts as YAML and Markdown, then exports to JSON on Cloudflare Pages (modelspec.dev). No database is on the serving path.

  • Site: modelspec.dev · decide
  • CLI contract: docs/cli-contract.md
  • Agent entry: AGENTS.md

Use ModelSpec

Use the free, rate-limited decision board. Machines have three ways in: the keyed CLI, the remote MCP Worker, and the HTTP API. Decisions require a ModelSpec API key. No data download and no local decision cache.

uvx --from modelspec-dev modelspec       # run without installing
pipx install modelspec-dev
pip install modelspec-dev

pip install modelspec is an unrelated project. Use modelspec-dev. Version 0.2.0 was yanked. 1.0.0 is the thin keyed client. It keeps modelspec compare. decide sends the bounded row list when the Spec omits fields.

Run modelspec or modelspec help agent --json for orientation, modelspec key for prices and access, and modelspec auth set to store a key in a 0600 file under your user config directory. MODELSPECAPIKEY wins. Then use modelspec decide --spec FILE|- or modelspec decide --template ID. modelspec setup mcp --client claude-desktop prints a client configuration; --write shows a diff and needs confirmation or --yes.

The CLI sends no telemetry and reads no provider API keys. Every error supplies next steps. See the agent guide, OpenAPI, pricing and keys, decision contract, and CLI contract.

Serving path

models/*.md ──▶ pipeline/build.py ──▶ static JSON on Cloudflare Pages
                                      (modelspec.dev /api/*.json)
                                            │
Hosted API ──────────────────────────────────┘

FalkorDB is optional local graph exploration only. It is not required to rank, fit, or render the sites.

Contribute

Read CONTRIBUTING.md. Sign off commits (git commit -s) to certify the DCO — not a copyright assignment. Every fact carries a source and the date it was read; unknown means an empty field.

Cards live in models/{provider}/{model-slug}.md. Edit and open a PR.

License

Two licences, because the code and the corpus want different things.

The corpus is share-alike: build on it, including commercially, but if you redistribute it or a derivative, credit ModelSpec and publish yours under the same terms. The CLI source remains MIT-licensed. Full text in LICENSE and LICENSE-DATA. See LICENSING.md.

Every card and page records the sources it draws on and the date each was read. Those sources keep their own licences.

Nothing above is checked by us. What we check is on the safety report.

ModelSpec: common questions

Is ModelSpec MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the ModelSpec safety report
How do I install ModelSpec?
It runs remotely at api.modelspec.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does ModelSpec need an API key?
Yes. The registry entry asks for Authorization.
Is ModelSpec maintained?
The last commit was 20 days ago (2026-10-15). The latest release is vb8da9336f3c5a0b56d47987251a29006a5b0487b.
Is ModelSpec up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does ModelSpec compare with other MCP servers?
safety score 85/100 (higher than 70% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.