# io.github.Creed-Space/creedspace-mcp-server (npm · @creedspace/mcp-server)

Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.

- Trust score: 60/100 (medium)
- Change this week: +14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@creedspace/mcp-server`: 60/100 (this document), [markdown](https://verifymcp.io/servers/creed-space-creedspace-mcp-server/creedspace-mcp-server.md), [page](https://verifymcp.io/servers/creed-space-creedspace-mcp-server/creedspace-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@creedspace/mcp-server`
- Version: `1.1.4`
- 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**: 75/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (125 of 127), so this covers what we could see, not the whole tree.
  - Install-script check failed: the install command fetches or executes arbitrary code (inline_eval). An install hook runs on every machine, in CI, and on transitive installs, whether or not you ever run the server.
  - Only part of the dependency tree could be resolved (125 of 127), 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 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 739 tokens (~46/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add creed-space-creedspace-mcp-server -- npx -y @creedspace/mcp-server
```

### Codex

```bash
codex mcp add creed-space-creedspace-mcp-server -- npx -y @creedspace/mcp-server
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add creed-space-creedspace-mcp-server --command npx --arg -y --arg @creedspace/mcp-server
```

### Hermes

```yaml
mcp_servers:
  creed-space-creedspace-mcp-server:
    command: "npx"
    args: ["-y", "@creedspace/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "creed-space-creedspace-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@creedspace/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 60, +24)

- [security regression] Install scripts: unverified → fail
- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [security] The scripts that run when this package is installed changed: postinstall
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 36, +31)

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

### 2026-07-31 (score 5, −68)

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

### 2026-07-29 (score 73, +48)

- [security regression] Install scripts: unverified → fail
- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security] The scripts that run when this package is installed changed: postinstall
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-07-28 (score 25, −21)

- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

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

First indexed and scored.

## MCP tools (16)

### `get_constitution` (~54 tokens)

Get the merged constitution for a specific persona, including all active rules and UVC qualities

Input parameters:

- `persona_id` (string): The persona ID (e.g., "ambassador", "nanny", "sentinel")

Output parameters:

- `content` (string): Merged constitution text
- `creedAttestation` (string): Attestation line binding this response to the active creed hash
- `icon` (string): Persona icon (emoji)
- `persona` (string): Human-readable persona name
- `totalRules` (number): Total number of rules in the merged creed
- `uvcToken` (string): UVC token, when configured for the persona

### `list_personas` (~21 tokens)

List all available AI personas with their descriptions and current status

Output parameters:

- `available` (array): All personas available from the Creed Space API
- `current` (string): Currently active persona ID for this session

### `set_persona` (~34 tokens)

Switch to a different AI persona for the current session

Input parameters:

- `persona_id` (string, required): The persona ID to switch to

Output parameters:

- `description` (string): Persona description
- `icon` (string): Persona icon (emoji)
- `id` (string): Persona ID
- `message` (string): Human-readable confirmation of the switch
- `name` (string): Human-readable persona name

### `get_uvc_qualities` (~40 tokens)

Get the desired, disliked, and never qualities for a persona from the UVC system

Input parameters:

- `persona_id` (string): The persona ID

Output parameters:

- `configured` (boolean): False when no UVC qualities are configured for the persona
- `personaId` (string): The persona the qualities belong to
- `qualities` (object|null): Value qualities for the persona; null when UVC is not configured

### `get_system_prompt` (~35 tokens)

Get a complete system prompt for a persona including constitution and UVC qualities

Input parameters:

- `persona_id` (string): The persona ID

Output parameters:

- `creedAttestation` (string): Attestation line binding the prompt to the active creed hash
- `personaId` (string): The persona the prompt was built for
- `systemPrompt` (string): Assembled system prompt text

### `preview_export` (~75 tokens)

Preview the export configuration for Claude Code or other AI tools

Input parameters:

- `include_constitutions` (boolean): Include constitutions in export
- `include_system_prompt` (boolean): Include system prompt in export
- `include_uvc` (boolean): Include UVC qualities in export
- `persona_id` (string): The persona ID

Output parameters:

- `constitutionIds` (array): Constitution IDs included in the export
- `includeConstitutions` (boolean): Whether constitutions were included
- `includeSystemPrompt` (boolean): Whether the system prompt was included
- `includeUvc` (boolean): Whether UVC qualities were included
- `personaId` (string): The persona the export was built for
- `personaName` (string): Human-readable persona name
- `preview` (string): Rendered export preview text

### `get_constitution_by_id` (~31 tokens)

Get a specific constitution by its ID

Input parameters:

- `constitution_id` (string, required): The constitution ID

Output parameters:

- `content` (string): Full constitution text
- `id` (string): Constitution ID
- `isSystemConstitution` (boolean): True for built-in system constitutions
- `name` (string): Constitution name
- `personaId` (string): Owning persona ID, when persona-scoped
- `uvcQualities` (object): Value qualities for the persona; null when UVC is not configured

### `search_constitutions` (~39 tokens)

Search constitutions by keyword or persona

Input parameters:

- `persona_id` (string): Filter by persona ID
- `query` (string): Search query

Output parameters:

- `constitutions` (array): Matching constitutions (content truncated to a 200-character preview)
- `persona` (string): Persona filter applied, or "all"
- `query` (string): Echo of the search query, when one was supplied
- `results` (number): Number of matching constitutions

### `get_active_persona` (~19 tokens)

Get the currently active persona for this session

Output parameters:

- `description` (string): Persona description
- `icon` (string): Persona icon (emoji)
- `id` (string): Persona ID
- `name` (string): Human-readable persona name

### `clear_cache` (~20 tokens)

Clear the local cache to force fresh data from the API

Output parameters:

- `cleared` (boolean): True once the local cache has been cleared
- `message` (string): Human-readable confirmation

### `adjudicate` (~66 tokens)

Get a policy decision kernel for a user request based on active constitutions and persona

Input parameters:

- `context` (object): Additional context for the decision
- `persona_id` (string): The persona ID for policy context
- `question` (string, required): The user question or request to adjudicate

Output parameters:

- `caveats` (array): Caveats to the verdict
- `decision` (string): Policy verdict (allow, block, modify, escalate, permit, forbid, divert, depends)
- `hash` (string): Kernel hash for verification
- `nonce` (string|null): Echo of the request nonce; null when none was supplied
- `norms` (array): Norms applied when reaching the decision
- `precedence` (array): Precedence ordering used to resolve conflicting norms
- `rationale` (string): Short explanation of the decision
- `sources` (array): Constitution sources cited by the decision
- `timestamp` (number): Unix timestamp of the decision
- `transparency` (object|null): Transparency detail; null unless a transparency level was requested

### `get_anchor` (~65 tokens)

Get a compact anchor (1-2KB) with top 10 non-negotiable rules and creed hash for quick context reinforcement

Input parameters:

- `max_length` (number): Maximum length of anchor in characters (100-2000)
- `persona_id` (string): The persona ID

Output parameters:

- `anchor` (string): Compact anchor text
- `maxLength` (number): Maximum length applied
- `persona` (string): Human-readable persona name
- `personaId` (string): The persona the anchor was built for
- `totalRules` (number): Total rules in the merged creed
- `truncated` (boolean): True when the anchor was cut to fit max_length

### `attest_response` (~50 tokens)

Validate a response against the active creed to check for violations and ensure attestation

Input parameters:

- `persona_id` (string): The persona ID to validate against
- `response` (string, required): The response text to validate

Output parameters:

- `attestationPresent` (boolean): Whether the response embeds the active creed hash
- `creedHash` (string|null): Active creed hash, or null when no creed has been fetched yet
- `status` (string): fail on violations, warn on warnings only, otherwise pass
- `violations` (array): Forbidden qualities detected in the response
- `warnings` (array): Non-blocking issues, e.g. a missing attestation

### `heartbeat` (~65 tokens)

Periodic re-anchoring to prevent context drift - returns mini-anchor every 10 messages

Input parameters:

- `force` (boolean): Force anchor return regardless of message count
- `message_count` (number): Current message count in the session
- `persona_id` (string): The persona ID

Output parameters:

- `anchored` (boolean): True when a mini-anchor was returned rather than a plain acknowledgement
- `messageCount` (number): Message count supplied by the caller
- `persona` (string): Human-readable persona name; present only when anchored
- `personaId` (string): The persona used for re-anchoring
- `text` (string): Mini-anchor text, or the heartbeat acknowledgement

### `perform_multi_scale_handshake` (~62 tokens)

Perform N-party value handshake across micro/meso/macro scales with anti-collusion and hierarchical budgets

Input parameters:

- `invariants` (array): List of invariant rules that must be enforced
- `parties` (array, required): Array of party contexts for handshake

Output parameters:

- `conflicts` (array): Conflicts detected between parties
- `party_weights` (object): Weight assigned to each party in the synthesis
- `precedence_decisions` (array): Precedence decisions taken to resolve competing party values
- `rationale` (string): Explanation of the handshake outcome
- `scale_attestations` (object): Attestation record per alignment scale
- `synthesized_constitution` (object|null): Merged UVC components agreed across parties; null when no synthesis was reached

### `get_scale_attestation` (~63 tokens)

Get attestation record with hash chain for a specific scale and entity

Input parameters:

- `entity_id` (string, required): Entity ID to get attestation for
- `include_chain` (boolean): Include parent hash chain
- `scale` (string, required): Scale level for attestation

Output parameters:

- `attestation` (object|null): Null when no attestation exists for the entity
- `chain` (array): Parent hash chain; present when include_chain was set
- `entity_id` (string): Entity the attestation belongs to
- `scale` (string): Alignment scale of the attestation

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/creed-space-creedspace-mcp-server/creedspace-mcp-server#diagnostics

## Score history

- 2026-08-03: 60
- 2026-08-02: 60
- 2026-08-01: 36
- 2026-07-31: 5
- 2026-07-30: 73
- 2026-07-29: 73
- 2026-07-28: 25
- 2026-07-27: 46

## Links

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