# PubFi MCP (remote · mcp.pubfi.ai)

Enumerate and inspect PubFi capabilities, then execute an exact selected route.

- Trust score: 69/100 (medium)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.pubfi.ai`: 69/100 (this document), [markdown](https://verifymcp.io/servers/ai-pubfi-mcp/mcp.md), [page](https://verifymcp.io/servers/ai-pubfi-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.pubfi.ai`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.79`

## 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 2026-08-03.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - 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**: 60/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 323 tokens (~107/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 8 days we've observed: 4 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 64% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-pubfi-mcp https://mcp.pubfi.ai/
```

### Codex

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

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-pubfi-mcp --url https://mcp.pubfi.ai/ --transport streamable-http
```

### Hermes

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

### Other

```json
{
  "mcpServers": {
    "ai-pubfi-mcp": {
      "type": "http",
      "url": "https://mcp.pubfi.ai/"
    }
  }
}
```

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.

### 2026-08-01 (score 69, +5)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 64, 0)

- [functional] Server version: 0.1.78 → 0.1.79

### 2026-07-30 (score 64, 0)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: fail → unverified
- [security regression] Authorization: fail → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional] First check of Schema quality: unverified
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server
- [functional] Server version: 0.1.76 → 0.1.77

### 2026-07-29 (score 64, +1)

- [security regression] Stability: 0.07 → fail
- [security regression] Tool “pubfi.capabilities.search” was removed
- [security regression] Tool “pubfi.route.explain” was removed
- [security regression] Tool “pubfi.route.plan” was removed
- [security regression] Tool “pubfi.schema.get” was removed
- [security] Tool “pubfi.route.execute” is now declared destructive
- [functional improvement] Schema quality: 544 → 323
- [functional improvement] Tool “pubfi.route.execute” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Server version: 0.1.74 → 0.1.76
- [functional] New tool “pubfi.capabilities.get”
- [functional] New tool “pubfi.capabilities.list”

### 2026-07-28 (score 63, +1)

- [functional] Server version: 0.1.63 → 0.1.74

### 2026-07-27 (score 62, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 61)

First indexed and scored.

## MCP tools (3)

### `pubfi.capabilities.list` (~99 tokens)

Enumerate the complete installed Registry v2 catalog as deterministic compact pages. The server does not rank, infer intent, or choose a capability.

Input parameters:

- `cursor` (string): Opaque generation-bound cursor returned by the preceding page.
- `limit` (integer): Maximum compact capability summaries to return.
- `method` (string)
- `provider_key` (string): Optional exact public provider key. This is a static filter, not semantic search.

Output parameters:

- `capabilities` (array)
- `compiled_at` (string)
- `filters` (object)
- `generation` (object)
- `manifest` (object)
- `matching_capability_count` (integer)
- `next_cursor` (string)
- `observed_at` (string)
- `schema_version`
- `total_capability_count` (integer)

### `pubfi.capabilities.get` (~54 tokens)

Return the full typed request, response, metering, and readiness contract for one exact capability id from the installed Registry generation.

Input parameters:

- `capability_id` (string, required): Exact capability id returned by pubfi.capabilities.list.

Output parameters:

- `capability` (object)
- `compiled_at` (string)
- `generation` (object)
- `manifest` (object)
- `observed_at` (string)
- `schema_version`

### `pubfi.route.execute` (~170 tokens)

Execute one exact GET or POST path through the same Registry v2 matcher, credential authority, and typed executor as the HTTP gateway. Use either an authenticated account lane with metering or the accountless x402 payment metadata lane.

Input parameters:

- `body` (string): Exact optional ASCII request-body bytes. For JSON routes, supply one compact serialized JSON document rather than a nested MCP argument value.
- `idempotency_key` (string)
- `method` (string, required)
- `query` (string): Exact ASCII raw query string without a leading question mark.
- `raw_path` (string, required): Exact original URI path consumed by the Registry matcher. Segments use canonical unreserved ASCII only; percent escapes, dot segments, query, fragment, and backslash are forbidden.
- `request_id` (string)

## Diagnostics

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

## Score history

- 2026-08-03: 69
- 2026-08-02: 69
- 2026-08-01: 69
- 2026-07-31: 64
- 2026-07-30: 64
- 2026-07-29: 64
- 2026-07-28: 63
- 2026-07-27: 62
- 2026-07-26: 61

## Links

- Remote endpoint: https://mcp.pubfi.ai/
- Repository: https://github.com/helixbox/pubfi-docs
- Website: https://pubfi.ai/agents.md
- Changelog RSS feed: https://verifymcp.io/servers/ai-pubfi-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-pubfi-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-pubfi-mcp/mcp