# ModelSpec (remote · api.modelspec.dev)

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

- Trust score: 56/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `api.modelspec.dev`: 56/100 (this document), [markdown](https://verifymcp.io/servers/turbobeest-modelspec/api.md), [page](https://verifymcp.io/servers/turbobeest-modelspec/api)

## Channel facts

- Endpoint: `https://api.modelspec.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `b8da9336f3c5a0b56d47987251a29006a5b0487b`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2347 tokens (~260/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 48% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the ModelSpec MCP server?

ModelSpec is a hosted endpoint at https://api.modelspec.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http turbobeest-modelspec 'https://api.modelspec.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "turbobeest-modelspec": {
      "url": "https://api.modelspec.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "turbobeest-modelspec": {
      "type": "http",
      "url": "https://api.modelspec.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.turbobeest-modelspec]
url = "https://api.modelspec.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "turbobeest-modelspec": {
      "type": "remote",
      "url": "https://api.modelspec.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add turbobeest-modelspec --url 'https://api.modelspec.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  turbobeest-modelspec:
    url: "https://api.modelspec.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "turbobeest-modelspec": {
      "Transport": "http",
      "Url": "https://api.modelspec.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add turbobeest-modelspec -t streamable-http -u 'https://api.modelspec.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "turbobeest-modelspec": {
      "type": "http",
      "url": "https://api.modelspec.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 56, −1)

- [security] Tool “compare_models” rewrote its description, which is the text the model reads
- [security] Tool “decide” rewrote its description, which is the text the model reads
- [security] Tool “feedback” rewrote its description, which is the text the model reads
- [security] Tool “list_use_cases” rewrote its description, which is the text the model reads
- [security] Tool “model_info” rewrote its description, which is the text the model reads
- [security] Tool “policy_check” rewrote its description, which is the text the model reads
- [security] Tool “rank” rewrote its description, which is the text the model reads
- [security] Tool “vocab” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 60% → 48%
- [functional improvement] Schema quality: 310 → 260
- [functional] Server version: 2b2e9a38f19012658f2b390cbb3f00eb8a00ae75 → b4a7074f37a3ba940bd86db9d1e2459a25fd40af
- [functional] New tool “hardware_fit”

### 2026-10-17 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 56, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0afd269c0e2e4dbb86dd073f4b8669437470fb07 → 2b2e9a38f19012658f2b390cbb3f00eb8a00ae75

### 2026-10-15 (score 56)

First indexed and scored.

## MCP tools (9)

### `rank` (~212 tokens)

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.

Input parameters:

- `constraints` (object)
- `environment` (object)
- `limit` (integer)
- `use_case` (string, required): Ranking profile id, as published in /api/rank/profiles.json

### `model_info` (~75 tokens)

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.

Input parameters:

- `model_id` (string, required): Catalogue id, e.g. openai/gpt-5-6

### `list_use_cases` (~47 tokens)

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.

### `policy_check` (~171 tokens)

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.

Input parameters:

- `limit` (integer)
- `models` (array)
- `offset` (integer)
- `platforms` (array)
- `policy` (object, required)
- `require_no_undetermined` (boolean)
- `verdicts` (array)

### `decide` (~713 tokens)

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:…

### `compare_models` (~147 tokens)

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.

Input parameters:

- `models` (array, required): 2 to 4 distinct catalogue ids, such as openai/gpt-5-6, in caller order

### `hardware_fit` (~181 tokens)

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.

Input parameters:

- `batch`
- `context`
- `device_count`
- `memory`: Optional memory override in decimal GB per device
- `model`
- `quantisation`
- `runtime`
- `sku`

### `vocab` (~288 tokens)

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.

Input parameters:

- `detail` (string): Full returns all display details; defaults to compact. Cross-section matches remain paged
- `id` (string): Full details for this exact, case-sensitive id; starter resolves across sections and intersects with search
- `ids` (array): Full details for these exact, case-sensitive ids; starter resolves across sections and intersects with search
- `limit` (integer): Page size; defaults to 20. Cross-section lookups page even full details and ids
- `offset` (integer): Skip this many ranked cross-section matches or compact section rows; defaults to 0
- `search` (string): Search every section's ids, labels, definitions, values and synonyms. All tokens rank first; else content tokens match, stopwords omitted. A miss returns nearest ids. A non-starter section scopes the…
- `section` (string): Defaults to starter; with search or id/ids searches every section except coverage. An explicit non-starter section scopes the lookup

### `feedback` (~168 tokens)

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.

Input parameters:

- `decision_id` (string): The decision_id of the answer this is about.
- `note` (string): Optional. What was wrong or right. Never a prompt, a key or personal details.
- `rating` (string, required): How the answer held up when you acted on it.
- `template` (string): Optional. The decision template you used.
- `trying_to_decide` (string): Optional. What you were trying to decide.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/turbobeest-modelspec/api#diagnostics

## Score history

- 2026-10-18: 56
- 2026-10-17: 57
- 2026-10-16: 56
- 2026-10-15: 56

## Common questions

### What is the ModelSpec MCP server?

ModelSpec is an MCP server listed in the public MCP registry as io.github.turbobeest/modelspec. Find AI models that fit a job from your requirements, sourced benchmarks and real cost. This page covers its hosted endpoint (https://api.modelspec.dev/mcp).

### Is the ModelSpec MCP server safe to use?

ModelSpec scores 56 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ModelSpec MCP server expose?

ModelSpec exposes 9 tools: rank, model_info, list_use_cases, policy_check, decide, and 4 more. Their descriptions and schemas cost roughly 2,002 tokens of context every time the server is loaded.

### Does the ModelSpec MCP server require authentication?

No. We connected to ModelSpec without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ModelSpec MCP server still maintained?

ModelSpec is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.modelspec.dev/mcp
- Authorisation metadata: https://api.modelspec.dev/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/turbobeest/modelspec
- Website: https://modelspec.dev/
- Changelog RSS feed: https://verifymcp.io/servers/turbobeest-modelspec/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/turbobeest-modelspec/api.json
- HTML version of this page: https://verifymcp.io/servers/turbobeest-modelspec/api