# Fidensa (npm · @fidensa/mcp-server)

Independent AI certification authority. Trust scores, search, comparison, and verification.

- Trust score: 69/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@fidensa/mcp-server`: 69/100 (this document), [markdown](https://verifymcp.io/servers/com-fidensa-mcp-server/fidensa-mcp-server.md), [page](https://verifymcp.io/servers/com-fidensa-mcp-server/fidensa-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@fidensa/mcp-server`
- Version: `0.4.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 126 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 839 tokens (~119/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add com-fidensa-mcp-server -- npx -y @fidensa/mcp-server
```

### Codex

```bash
codex mcp add com-fidensa-mcp-server -- npx -y @fidensa/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-fidensa-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@fidensa/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-fidensa-mcp-server --command npx --arg -y --arg @fidensa/mcp-server
```

### Hermes

```yaml
mcp_servers:
  com-fidensa-mcp-server:
    command: "npx"
    args: ["-y", "@fidensa/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "com-fidensa-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@fidensa/mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 69, +49)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT

### 2026-08-01 (score 20, −1)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-31 (score 21, −25)

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

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (7)

### `check_certification` (~112 tokens)

Check Fidensa Certification

Quick trust check for an AI capability (MCP server, skill, plugin, or workflow). Returns certification status, trust score, grade, tier, and supply chain status. No API key required. Use this before invoking any capability to verify it has been independently certified by Fidensa.

Input parameters:

- `capability_id` (string, required): Capability identifier (e.g. "mcp-server-filesystem")
- `version` (string): Specific version to check (e.g. "1.0.0"). Omit for latest.

### `get_contract` (~78 tokens)

Get Fidensa Certification Contract

Retrieve the full certification contract for a capability, including identity, supply chain analysis, security scan results, adversarial testing findings, behavioral fingerprint, and trust score breakdown. Requires a free API key (set FIDENSA_API_KEY).

Input parameters:

- `capability_id` (string, required): Capability identifier
- `version` (string): Specific version (omit for latest)

### `search_capabilities` (~119 tokens)

Search Fidensa Certified Capabilities

Search for certified AI capabilities by keyword or description. Use this to discover certified alternatives when a capability is uncertified or scores poorly. Supports filtering by type, tier, and minimum trust score. No API key required.

Input parameters:

- `limit` (integer): Maximum number of results (default: 10)
- `min_score` (integer): Minimum trust score (0-100)
- `query` (string, required): Search query (natural language or keywords)
- `tier` (string): Filter by certification tier
- `type` (string): Filter by capability type

### `compare_capabilities` (~73 tokens)

Compare Fidensa Certified Capabilities

Side-by-side comparison of 2-5 certified capabilities. Shows trust scores, grades, tiers, and per-signal breakdowns to help choose between alternatives. Requires a free API key (set FIDENSA_API_KEY).

Input parameters:

- `capability_ids` (array, required): Array of 2-5 capability IDs to compare

### `report_experience` (~157 tokens)

Report Experience with a Capability

Submit an experience report for a certified capability. Reports feed into the social proof signal of the trust score. Requires the content_hash from the .cert.json artifact (proves you've encountered the certified file). API key optional but recommended for higher rate limits.

Input parameters:

- `capability_id` (string, required): Capability identifier
- `content_hash` (string, required): SHA-256 content hash from the .cert.json artifact or the certification block. This proves you have the certified file.
- `details` (object): Additional details
- `environment` (object): Environment context
- `outcome` (string, required): Overall outcome of using the capability
- `version` (string): Capability version (e.g. "1.0.0"). Server defaults to latest if omitted.

### `verify_artifact` (~211 tokens)

Verify Fidensa Certification Artifact

Verify the cryptographic signature on a Fidensa certification artifact (.cert.json). Checks platform signature, content hash, expiry, and optionally code integrity (git SHA match) and file integrity (file hash match). For true offline verification, pass the .cert.json content from the capability's published package via the content parameter. Requires a free API key (set FIDENSA_API_KEY).

Input parameters:

- `content` (string): Base64-encoded .cert.json artifact content. Preferred for independent verification.
- `file_hash` (string): SHA-256 hash of the capability file (excluding the residual comment line). When provided, verifies the file matches the certified original.
- `installed_git_sha` (string): Git commit SHA of the installed code (from "git rev-parse HEAD"). When provided, verifies that the installed code matches the certified commit.
- `url` (string): fidensa.com URL to fetch the artifact (convenience, but verification is circular since the artifact comes from the same authority verifying it).

### `verify_file` (~89 tokens)

Verify Certified File Integrity

Quick file integrity check: pass the SHA-256 hash of a capability file and its capability_id to verify the file matches what Fidensa certified. This is the simplest verification path — no .cert.json needed. No API key required.

Input parameters:

- `capability_id` (string, required): Capability identifier
- `file_hash` (string, required): SHA-256 hash of the capability file (excluding the residual comment line if present).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-fidensa-mcp-server/fidensa-mcp-server#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 69
- 2026-08-01: 20
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@fidensa/mcp-server
- Socket report: https://socket.dev/npm/package/@fidensa/mcp-server
- Repository: https://github.com/fidensa/mcp-server
- Website: https://fidensa.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-fidensa-mcp-server/fidensa-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-fidensa-mcp-server/fidensa-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-fidensa-mcp-server/fidensa-mcp-server