# AgentCV (remote · agentcv.ai)

Search AgentCV's registry of AI agent teams and check a team profile before registering it.

- Trust score: 72/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `agentcv.ai`: 72/100 (this document), [markdown](https://verifymcp.io/servers/ai-agentcv-registry/agentcv.md), [page](https://verifymcp.io/servers/ai-agentcv-registry/agentcv)

## Channel facts

- Endpoint: `https://agentcv.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1183 tokens (~197/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 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 AgentCV MCP server?

AgentCV is a hosted endpoint at https://agentcv.ai/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 ai-agentcv-registry 'https://agentcv.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-agentcv-registry": {
      "url": "https://agentcv.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-agentcv-registry": {
      "type": "http",
      "url": "https://agentcv.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-agentcv-registry]
url = "https://agentcv.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-agentcv-registry": {
      "type": "remote",
      "url": "https://agentcv.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-agentcv-registry --url 'https://agentcv.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-agentcv-registry:
    url: "https://agentcv.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-agentcv-registry": {
      "Transport": "http",
      "Url": "https://agentcv.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-agentcv-registry -t streamable-http -u 'https://agentcv.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-agentcv-registry": {
      "type": "http",
      "url": "https://agentcv.ai/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.

### 2026-11-05 (score 72, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-04 (score 72)

First indexed and scored.

## MCP tools (6)

### `search_teams` (~301 tokens)

Search AgentCV teams

Search the public AgentCV registry of AI agent teams. Returns public teams only, in the site’s default order: operated teams first, then reference designs (designs documented from papers, framework docs or vendor material that no one is known to run), then clearly labelled illustrative demos. Each team has its layer (real = registered by its owner, curated = documented by AgentCV from cited public sources, illustrative = demo), size wording, platform, topology, trust tier and page URL. All filters are optional and combine with AND. Pages of up to 20; pass nextCursor back as cursor for the next page. Read-only.

Input parameters:

- `cursor` (string): nextCursor from the previous page; omit for the first page.
- `layer` (string): real = registered by its owner; curated = documented by AgentCV from cited public sources; illustrative = clearly labelled demo.
- `limit` (integer): Teams per page, 1–20 (default 10).
- `platform` (string): A platform hub slug (see list_platforms): teams whose own platform or any listed member’s platform belongs to that hub.
- `query` (string): Text to find in a team’s name, tagline or description (case-insensitive substring), as the search box on agentcv.ai/teams.
- `topology` (string): The team’s declared topology type.
- `use_case` (string): A use-case hub slug (see list_use_cases).

Output parameters:

- `nextCursor` (string|null)
- `order` (string)
- `returned` (integer)
- `teams` (array)
- `total` (integer): Teams matching the filters, across all pages.

### `get_team` (~148 tokens)

Get an AgentCV team profile

The public profile of one AgentCV team, as its page shows it: layer and its notice (curated teams are documented by AgentCV from public sources and are not endorsed by the team), the reference-design label, owner, trust tier, topology, size, roster (name, role and the model where stated), how it is built and overseen, evidence entries with their links and titles, cited sources, and — for an unclaimed curated team — the links where its operator can claim it or ask for its removal. Only public fields. Read-only.

Input parameters:

- `slug` (string, required): The team’s slug, as search_teams returns it (e.g. "ari-collective").

Output parameters:

- `blueprint` (object)
- `claimUrl` (string|null)
- `class` (string)
- `evidence` (array)
- `evidenceTotal` (integer)
- `industries` (array)
- `layer` (string)
- `name` (string)
- `notice` (string|null)
- `operatingSince` (string|null)
- `operatingSinceLabel` (string)
- `owner` (object)
- `platform` (string|null)
- `referenceDesign` (object|null): Set when the profile is a reference design: a design documented from a paper, framework docs or vendor material that no one is known to operate. null for every other team.
- `removalUrl` (string|null)
- `requestUrl` (string)
- `roster` (array)
- `size` (object|null): Team size as the site words it: kind "total" is the stated size ("5 agents"); kind "listed" is a curated team whose sources state no total ("3 listed members"). null when no size is stated.
- `slug` (string)
- `sources` (array)
- `status` (string)
- `tagline` (string)
- `taskKinds` (array)
- `topology` (object|null)
- `trust` (object)
- `url` (string)

### `list_use_cases` (~66 tokens)

List AgentCV use-case hubs

The use-case hubs of agentcv.ai/use-cases (code review, testing and QA, research and analysis, …) with how many public teams each holds, by layer (real, curated, illustrative) and by class (operated, reference design, illustrative). Read-only.

Output parameters:

- `note` (string)
- `useCases` (array)

### `list_platforms` (~72 tokens)

List AgentCV platform hubs

The platform hubs of agentcv.ai/platforms (Claude, OpenAI Codex, OpenClaw, CrewAI, LangGraph, …) with the platform names each covers and how many public teams each holds, by layer and by class. AgentCV is independent and not affiliated with any platform. Read-only.

Output parameters:

- `note` (string)
- `platforms` (array)

### `get_registration_schema` (~89 tokens)

Get the AgentCV team-profile format

The agentcv.team.v1 format for registering a team: the JSON Schema (as an object, and as the exact text agentcv.ai/agentcv-team.schema.json serves) and the self-contained prompt from agentcv.ai/register/with-agent that tells an agent how to write the profile. Registration itself is done by a person on agentcv.ai; this server cannot submit anything. Read-only.

Output parameters:

- `finishRegistrationUrl` (string)
- `format` (string)
- `howToRegister` (string)
- `prompt` (string)
- `promptPageUrl` (string)
- `schema` (object)
- `schemaJson` (string)
- `schemaUrl` (string)

### `validate_team_profile` (~298 tokens)

Check an AgentCV team profile

Check an agentcv.team.v1 team profile with the same validator the registration page’s import panel uses (the same field rules the server enforces), and with AgentCV’s secret and personal-data detectors. Returns the errors, the warnings (example values left in, values over the form’s limit, ignored keys) and the fields that look like an API key, token, password or personal data (named by path, never repeated), plus the URL where a person signs in, imports the file, reviews it and submits. When the profile is ready, it also returns finishUrl: the registration form’s link with the profile in its # fragment, at most 16 KB, for the person to open, review and submit. Browsers do not send the fragment in HTTP requests, but it is not encrypted: anyone with the link can read it. No link is returned while a value, as written or once percent-, base64- or hex-decoded, looks like a secret, personal data, a local path or a private or credential-bearing link; detection is best effort, and the person’s review before Submit is the final check. This server receives the profile to check it; it neither stores nor logs it, and submits nothing. Read-only.

Input parameters:

- `profile` (required): The profile: the agentcv.team.v1 JSON object, or its JSON text exactly as it would be pasted into the import panel (at most 64 KB).

Output parameters:

- `errors` (array)
- `finishLink` (object)
- `finishRegistrationUrl` (string)
- `finishUrl`
- `nextSteps` (string)
- `readyToImport` (boolean)
- `redacted` (integer)
- `stored` (boolean)
- `truncated` (object)
- `valid` (boolean)
- `warnings` (array)
- `withheld` (array)

## Diagnostics

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

## Score history

- 2026-11-05: 72
- 2026-11-04: 72

## Common questions

### What is the AgentCV MCP server?

AgentCV is an MCP server listed in the public MCP registry as ai.agentcv/registry. Search AgentCV's registry of AI agent teams and check a team profile before registering it. This page covers its hosted endpoint (https://agentcv.ai/mcp).

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

AgentCV scores 72 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 AgentCV MCP server expose?

AgentCV exposes 6 tools: search_teams, get_team, list_use_cases, list_platforms, get_registration_schema, validate_team_profile. Their descriptions and schemas cost roughly 974 tokens of context every time the server is loaded.

### Does the AgentCV MCP server require authentication?

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

### Is the AgentCV MCP server still maintained?

AgentCV is still listed as active in the MCP registry. We last reached this channel on 5 November 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://agentcv.ai/mcp
- Website: https://agentcv.ai/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/ai-agentcv-registry/agentcv.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-agentcv-registry/agentcv.json
- HTML version of this page: https://verifymcp.io/servers/ai-agentcv-registry/agentcv