Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Creed-Space/creedspace-mcp-server

NPM · @CREEDSPACE/MCP-SERVER

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

0 this week 74 Trust /100

Last scanned (19 hours ago)

Scores higher than 49% of npm servers

Category AI and Machine Learning

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security68
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • 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. View diagnostics → Fail
  • 40 of 124 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability70
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 739 tokens (~46/item across 16 items; 16 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 0
    • Stability: 0.97 → pass security
  • 18 Nov 26 0
    • Stability: pass → 0.97 functional
  • 12 Nov 26 0
    • Stability: 0.97 → pass security
    • Security disclosure: unverified → fail ▼ functional
  • 11 Nov 26 +1
    • Security disclosure: fail → unverified ▼ functional
  • 9 Nov 26 −1
    • Stability: pass → 0.90 functional
  • 3 Nov 26 0
    • Stability: 0.97 → pass security
  • 2 Nov 26 0
    • Stability: pass → 0.97 functional
  • 27 Oct 26 0
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/@creedspace/mcp-server@1.1.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
postinstall Dropper pattern node -e "try{const f='./dist/postinstall.js';require('fs').existsSync(f)&&require(f)}catch{}"

Background: Why install scripts are a supply-chain risk →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 124 packages
Packages resolved 124
Stale 40
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 16 exposed · ~739 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
adjudicate ~66

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

NameTypeReqDescription
contextobject–Additional context for the decision
persona_idstring–The persona ID for policy context
questionstringyesThe user question or request to adjudicate
NameTypeReqDescription
caveatsarray–Caveats to the verdict
decisionstring–Policy verdict (allow, block, modify, escalate, permit, forbid, divert, depends)
hashstring–Kernel hash for verification
noncestring|null–Echo of the request nonce; null when none was supplied
normsarray–Norms applied when reaching the decision
precedencearray–Precedence ordering used to resolve conflicting norms
rationalestring–Short explanation of the decision
sourcesarray–Constitution sources cited by the decision
timestampnumber–Unix timestamp of the decision
transparencyobject|null–Transparency detail; null unless a transparency level was requested

No examples provided.

attest_response ~50

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

NameTypeReqDescription
persona_idstring–The persona ID to validate against
responsestringyesThe response text to validate
NameTypeReqDescription
attestationPresentbooleanyesWhether the response embeds the active creed hash
creedHashstring|null–Active creed hash, or null when no creed has been fetched yet
statusstringyesfail on violations, warn on warnings only, otherwise pass
violationsarrayyesForbidden qualities detected in the response
warningsarrayyesNon-blocking issues, e.g. a missing attestation

No examples provided.

clear_cache ~20

Clear the local cache to force fresh data from the API

Input schema present but exposes no named parameters.

NameTypeReqDescription
clearedbooleanyesTrue once the local cache has been cleared
messagestringyesHuman-readable confirmation

No examples provided.

get_active_persona ~19

Get the currently active persona for this session

Input schema present but exposes no named parameters.

NameTypeReqDescription
descriptionstringyesPersona description
iconstringyesPersona icon (emoji)
idstringyesPersona ID
namestringyesHuman-readable persona name

No examples provided.

get_anchor ~65

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

NameTypeReqDescription
max_lengthnumber–Maximum length of anchor in characters (100-2000)
persona_idstring–The persona ID
NameTypeReqDescription
anchorstringyesCompact anchor text
maxLengthnumberyesMaximum length applied
personastringyesHuman-readable persona name
personaIdstringyesThe persona the anchor was built for
totalRulesnumber–Total rules in the merged creed
truncatedbooleanyesTrue when the anchor was cut to fit max_length

No examples provided.

get_constitution ~54

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

NameTypeReqDescription
persona_idstring–The persona ID (e.g., "ambassador", "nanny", "sentinel")
NameTypeReqDescription
contentstringyesMerged constitution text
creedAttestationstring–Attestation line binding this response to the active creed hash
iconstring–Persona icon (emoji)
personastringyesHuman-readable persona name
totalRulesnumberyesTotal number of rules in the merged creed
uvcTokenstring–UVC token, when configured for the persona

No examples provided.

get_constitution_by_id ~31

Get a specific constitution by its ID

NameTypeReqDescription
constitution_idstringyesThe constitution ID
NameTypeReqDescription
contentstringyesFull constitution text
idstringyesConstitution ID
isSystemConstitutionbooleanyesTrue for built-in system constitutions
namestringyesConstitution name
personaIdstring–Owning persona ID, when persona-scoped
uvcQualitiesobject–Value qualities for the persona; null when UVC is not configured

No examples provided.

get_scale_attestation ~63

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

NameTypeReqDescription
entity_idstringyesEntity ID to get attestation for
include_chainboolean–Include parent hash chain
scalestringyesScale level for attestation
NameTypeReqDescription
attestationobject|null–Null when no attestation exists for the entity
chainarray–Parent hash chain; present when include_chain was set
entity_idstring–Entity the attestation belongs to
scalestring–Alignment scale of the attestation

No examples provided.

get_system_prompt ~35

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

NameTypeReqDescription
persona_idstring–The persona ID
NameTypeReqDescription
creedAttestationstringyesAttestation line binding the prompt to the active creed hash
personaIdstringyesThe persona the prompt was built for
systemPromptstringyesAssembled system prompt text

No examples provided.

get_uvc_qualities ~40

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

NameTypeReqDescription
persona_idstring–The persona ID
NameTypeReqDescription
configuredbooleanyesFalse when no UVC qualities are configured for the persona
personaIdstringyesThe persona the qualities belong to
qualitiesobject|null–Value qualities for the persona; null when UVC is not configured

No examples provided.

heartbeat ~65

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

NameTypeReqDescription
forceboolean–Force anchor return regardless of message count
message_countnumber–Current message count in the session
persona_idstring–The persona ID
NameTypeReqDescription
anchoredbooleanyesTrue when a mini-anchor was returned rather than a plain acknowledgement
messageCountnumberyesMessage count supplied by the caller
personastring–Human-readable persona name; present only when anchored
personaIdstringyesThe persona used for re-anchoring
textstringyesMini-anchor text, or the heartbeat acknowledgement

No examples provided.

list_personas ~21

List all available AI personas with their descriptions and current status

Input schema present but exposes no named parameters.

NameTypeReqDescription
availablearrayyesAll personas available from the Creed Space API
currentstringyesCurrently active persona ID for this session

No examples provided.

perform_multi_scale_handshake ~62

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

NameTypeReqDescription
invariantsarray–List of invariant rules that must be enforced
partiesarrayyesArray of party contexts for handshake
NameTypeReqDescription
conflictsarray–Conflicts detected between parties
party_weightsobject–Weight assigned to each party in the synthesis
precedence_decisionsarray–Precedence decisions taken to resolve competing party values
rationalestring–Explanation of the handshake outcome
scale_attestationsobject–Attestation record per alignment scale
synthesized_constitutionobject|null–Merged UVC components agreed across parties; null when no synthesis was reached

No examples provided.

preview_export ~75

Preview the export configuration for Claude Code or other AI tools

NameTypeReqDescription
include_constitutionsboolean–Include constitutions in export
include_system_promptboolean–Include system prompt in export
include_uvcboolean–Include UVC qualities in export
persona_idstring–The persona ID
NameTypeReqDescription
constitutionIdsarray–Constitution IDs included in the export
includeConstitutionsboolean–Whether constitutions were included
includeSystemPromptboolean–Whether the system prompt was included
includeUvcboolean–Whether UVC qualities were included
personaIdstringyesThe persona the export was built for
personaNamestringyesHuman-readable persona name
previewstringyesRendered export preview text

No examples provided.

search_constitutions ~39

Search constitutions by keyword or persona

NameTypeReqDescription
persona_idstring–Filter by persona ID
querystring–Search query
NameTypeReqDescription
constitutionsarrayyesMatching constitutions (content truncated to a 200-character preview)
personastringyesPersona filter applied, or "all"
querystring–Echo of the search query, when one was supplied
resultsnumberyesNumber of matching constitutions

No examples provided.

set_persona ~34

Switch to a different AI persona for the current session

NameTypeReqDescription
persona_idstringyesThe persona ID to switch to
NameTypeReqDescription
descriptionstringyesPersona description
iconstringyesPersona icon (emoji)
idstringyesPersona ID
messagestringyesHuman-readable confirmation of the switch
namestringyesHuman-readable persona name

No examples provided.

Install

How do I install the io.github.Creed-Space/creedspace-mcp-server server?

io.github.Creed-Space/creedspace-mcp-server runs locally as an npm package, launched with npx -y @creedspace/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @creedspace/mcp-server

# add to Claude Code
claude mcp add creed-space-creedspace-mcp-server -- npx -y @creedspace/mcp-server
Common questions

What is the io.github.Creed-Space/creedspace-mcp-server server?

io.github.Creed-Space/creedspace-mcp-server is listed in the public MCP registry as io.github.Creed-Space/creedspace-mcp-server. Constitutional-AI safety guardrails for any LLM, personas, constitutions, adjudication. This page covers its npm package (@creedspace/mcp-server).

Is the io.github.Creed-Space/creedspace-mcp-server server safe to use?

io.github.Creed-Space/creedspace-mcp-server scores 74 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares an install script we flagged as high risk. 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 io.github.Creed-Space/creedspace-mcp-server server expose?

io.github.Creed-Space/creedspace-mcp-server exposes 16 tools: get_constitution, list_personas, set_persona, get_uvc_qualities, get_system_prompt, and 11 more. Their descriptions and schemas cost roughly 739 tokens of context every time the server is loaded.

Is the io.github.Creed-Space/creedspace-mcp-server server still maintained?

io.github.Creed-Space/creedspace-mcp-server is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.Creed-Space/creedspace-mcp-server server under?

io.github.Creed-Space/creedspace-mcp-server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.Creed-Space/creedspace-mcp-server server?

VerifyMCP ran 16 checks on io.github.Creed-Space/creedspace-mcp-server, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.