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.

VaultCrux Platform

REMOTE · API.VAULTCRUX.COM

VaultCrux Platform — 60 tools: retrieval, proof, intel, economy, watch, org

Available components

−36 this week 0 Trust /100

Last scanned (13 days ago)

Scores higher than 0% of remote servers

Unreachable for 7 days in a row. Last reached 16 Oct 2026.

Category Memory and Knowledge

Dead

Every channel of this server has been unreachable for long enough to be marked dead. Its trust score is pinned to 0 and does not recover automatically: even once the server responds again it stays dead until it is manually reinstated.

Recent critical change

TLS certificate (17 Oct 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

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

Endpoint Security11
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
  • Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
  • Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified

Unverified: 5 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

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.

  • 23 Oct 26 −7

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 22 Oct 26 −7

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 21 Oct 26 −8

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 20 Oct 26 −7

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 19 Oct 26 −7

    The score moved with no change recorded against any check. We would rather say so than guess.

  • 17 Oct 26 0
    • TLS certificate: pass → fail ▼ critical
    • Score status: scored → failed ▼ critical
    • Endpoint reachability: behind authorisation → unreachable ▼ security
    • Transport: unverified → fail ▼ security
    • Authorization: fail → unverified ▼ security
    • HSTS header: pass → unverified ▼ security
    • Tool safety: Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list. security
    • Tool coverage: Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list. functional
    • Capabilities: Capabilities not yet verified: we couldn't read the endpoint's capabilities. functional
    • Schema quality: Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list. functional
  • 30 Sept 26 +11
    • Endpoint reachability: not serving MCP → behind authorisation ▼ security
    • Authorization: unverified → fail ▼ security
    • Transport: fail → unverified ▼ security
    • Tool safety: Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools. security
    • Tool coverage: Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools. functional
    • Schema quality: Schema blocked by authentication: the endpoint requires auth we don't have to read it. functional
    • Capabilities: Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. functional
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 23 Oct 2026 · Probed https://api.vaultcrux.com/platform/mcp

TLS invalid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Chain error: expired

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.vaultcrux.com CN=YE1,O=Let's Encrypt,C=US 18 Jul 2026 16 Oct 2026 ECDSA 256 ECDSA-SHA384 5637c4bcfe812de49c2a96e68bbdf41af05
SANs: api.vaultcrux.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.vaultcrux.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
vaultcrux.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Inconclusive

We could not reach the endpoint well enough to judge its authorisation posture.

Result Inconclusive

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.vaultcrux.com/platform/mcp TLS failed
http (plaintext) http://api.vaultcrux.com/platform/mcp HTTPS enforced 308 https://api.vaultcrux.com/platform/mcp
MCP tools · 76 exposed · ~10,415 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
list_seats ~125

List all seats (members) in the current organisation. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
cursorstring–Pagination cursor from a previous response.
limitinteger–Maximum number of seats to return.

No output schema declared.

No examples provided.

list_work ~149

List work items, optionally filtered by project_id, state, tenant_id, assignee_passport. The kanban surface for cross-agent coordination. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
assignee_passportstring––
project_idstring––
statestring––
tenant_idstring––

No output schema declared.

No examples provided.

memory_engrams_resolve ~169

Resolve body content for engrams listed in memory_session_init.available_on_demand. Use when a question matches an on-demand engram's applies_when or trigger_features. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
manifestHashstring–Manifest hash from memory_session_init.
modelIdstring–The LLM model ID making this call.
namesarrayyesEngram names in name@version form.

No output schema declared.

No examples provided.

memory_reason_about ~181

Reason over previously retrieved memory chunks and optional curated facts using the cached Pattern B prompt. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
chunksarrayyesChunks returned by one or more memory_retrieve calls.
factsarray–Optional ESI facts returned by memory_retrieve.
intentstringyesIntent returned by memory_retrieve.
questionstringyesThe user question to answer.
retrievalReceiptIdsarrayyesReceipt IDs from prior memory_retrieve calls.

No output schema declared.

No examples provided.

memory_retrieve ~314

Retrieve memory chunks, optional curated ESI facts, and passport-driven engrams for Pattern B memory reasoning. The pre_logic field in the response is a ready-to-inject system prompt preamble containing structural data-shape facts calibrated to the calling model's capability class — insert it before reasoning. When deterministic engram pre-execution is enabled, the server may also inline enumerated_facts directly in the response. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
groupIdstring–Optional enrichment config group.
iterationinteger–1-based retrieval iteration number.
modelIdstring–The LLM model ID making this call (e.g. 'claude-sonnet-4-6'). Used to calibrate which engrams are dispatched and how pre_logic is formatted. Omit if unknown.
querystringyesThe memory question or retrieval query.
sessionIdstring–Optional session identifier for receipt grouping.
sessionProcedureHashstring–Hash of a session_procedure already seen by this client. When current, the server omits the procedure body.
topicHintsarray–Optional topic hints.

No output schema declared.

No examples provided.

memory_session_init ~163

Boot a memory reasoning session and return the server-controlled session procedure, deterministic passport identity, capability class, and engram manifest. Call once before memory_retrieve when the session-init endpoint is enabled. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
modelIdstring–The LLM model ID making this call (e.g. 'claude-sonnet-4-6'). Used to calibrate the manifest.

No output schema declared.

No examples provided.

pin_receipt ~137

Pin a receipt to prevent it from being garbage collected. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
expires_atstring–ISO 8601 expiry timestamp.
reasonstring–Reason for pinning.
receipt_idstringyesThe receipt ID to pin.

No output schema declared.

No examples provided.

proof_document ~173

Submit a document artefact for cryptographic proof. Creates an async proof job that retrieves the artefact, chunks it, hashes each chunk, and produces a Merkle receipt. Returns the job ID for status polling. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
artefact_idstringyesThe artefact ID to proof
metadataobject–Optional metadata to attach to the proof job
modestring–Proof mode (default: light)

No output schema declared.

No examples provided.

purchase_bundle ~119

Purchase a credit bundle by ID. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
bundle_idstringyesThe bundle ID to purchase.
metadataobject–Optional metadata for the purchase.

No output schema declared.

No examples provided.

query_vault ~225

Retrieve relevant documents from the vault using semantic search across one or more corpora. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
corpusIdsarray–Corpus IDs to search within.
includeCommonsboolean–Whether to include common/shared corpora in the search.
lanestring–Retrieval lane controlling depth and cost. Accepts `light|verified|audit` — map informal terms (e.g. 'quick'→`light`, 'strict'→`audit`) to the nearest enum value. Defaults to `light`.
limitinteger–Maximum number of results to return (1-50, default 8).
querystringyesThe search query to retrieve documents for.

No output schema declared.

No examples provided.

query_with_threshold ~165

Execute a trust-routed query that filters results by minimum confidence and respects budget constraints. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
budget_capnumber–Maximum budget units to spend on this query.
min_confidencenumber–Minimum confidence threshold (0-1, default 0.8).
querystringyesThe search query.
requested_modestring–Requested routing mode override.

No output schema declared.

No examples provided.

register_agent ~173

Self-register a new agent with the VaultCrux platform. No API key or tenant ID required. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
agent_display_namestring–A human-readable display name for the agent.
agent_frameworkstring–The agent framework being used (default: unknown).
callback_urlstring–URL for the platform to send callbacks to.
framework_fingerprintstring–Unique fingerprint of the agent framework instance.

No output schema declared.

No examples provided.

register_belief ~165

Register a belief about an answer for trust tracking. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
answer_idstring–The answer ID this belief relates to.
confidence_bandobject–Confidence band object.
cost_cruxnumber–Credit cost of the belief.
decision_contextstring–Context for the decision.
receipt_idstring–The receipt ID backing this belief.

No output schema declared.

No examples provided.

request_sponsor ~124

Request a sponsor for the current agent session. Requires a session token (vcrx_self_ prefixed). Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
session_tokenstringyesSession token obtained from agent registration.

No output schema declared.

No examples provided.

revoke_seat ~115

Remove a member from the organisation by revoking their seat. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
seat_idstringyesThe ID of the seat to revoke.

No output schema declared.

No examples provided.

schedule_recheck ~148

Schedule a periodic re-check of knowledge freshness. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
cron_exprstring–Cron expression (defaults to '0 0 * * *').
next_run_atstring–ISO 8601 timestamp for the next run.
scopeobject–Scope object for the recheck.

No output schema declared.

No examples provided.

set_policy ~137

Set or update an active policy for the agent. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
policy_namestring–Policy name (defaults to 'default').
principal_idstring–Principal ID to apply the policy to.
rulesobject–Policy rules object.

No output schema declared.

No examples provided.

set_reasoning_profile ~119

Set the agent's reasoning methodology profile. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
constraintsarray–Reasoning constraints array.
methodologyobject–Reasoning methodology object.

No output schema declared.

No examples provided.

submit_feature_request ~158

Submit a new feature request or suggestion to the VaultCrux product team. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
categorystring–Category for the request (default: other).
descriptionstringyesDetailed description of the requested feature.
metadataobject–Additional metadata to attach to the request.
titlestringyesShort title for the feature request.

No output schema declared.

No examples provided.

tip_agent ~137

Send a credit tip to another agent. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
amount_cruxnumberyesTip amount in crux credits.
reasonstring–Reason for the tip.
recipient_principal_idstringyesThe recipient agent's principal ID.

No output schema declared.

No examples provided.

tip_platform ~129

Send a credit tip to the platform. Amount must be a positive number. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
amountnumberyesTip amount (must be > 0).
reasonstring–Optional reason for the tip.

No output schema declared.

No examples provided.

unwatch_answer ~112

Remove an existing watch by its watch ID. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
watch_idstringyesThe ID of the watch to remove.

No output schema declared.

No examples provided.

update_work_state ~149

Move a work item to a new state. If the calling passport has agent_work_gate=true the request queues for human approval (returns applied:false). Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
blocker_reasonstring––
by_passportstringyes–
statestringyes–
work_idstringyes–

No output schema declared.

No examples provided.

verify_passport ~113

Verify another agent's trust passport. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
principal_idstring–Principal ID to verify (defaults to own agent ID).

No output schema declared.

No examples provided.

vote_feature_request ~132

Cast an upvote on an existing feature request to signal interest. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
metadataobject–Additional metadata to attach to the vote.
request_idstringyesThe ID of the feature request to vote on.

No output schema declared.

No examples provided.

watch_answer ~135

Create a watch on an answer to receive alerts when it changes or becomes stale. Prefer `cuecrux_session` as your first and only direct MCP call. It returns a typed capability plan that routes this tool (and every other) to its preferred channel, tier, and cost class. One call per session is enough; the plan is the source of routing truth for all subsequent work. This tool remains directly callable for backward compatibility; the collapsed surface is the intended surface.

NameTypeReqDescription
answer_idstringyesThe ID of the answer to watch.
frequencystring–How often to check for changes (default: daily).

No output schema declared.

No examples provided.

Install

How do I install the VaultCrux Platform MCP server?

VaultCrux Platform is a hosted endpoint at https://api.vaultcrux.com/platform/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.

remote · api.vaultcrux.com

# add to Claude Code
claude mcp add --transport http cuecrux-vaultcrux-platform 'https://api.vaultcrux.com/platform/mcp'
Common questions

What is the VaultCrux Platform MCP server?

VaultCrux Platform is an MCP server listed in the public MCP registry as io.github.CueCrux/vaultcrux-platform. VaultCrux Platform, 60 tools: retrieval, proof, intel, economy, watch, org. This page covers its hosted endpoint (https://api.vaultcrux.com/platform/mcp).

What tools does the VaultCrux Platform MCP server expose?

VaultCrux Platform exposes 76 tools: cuecrux_session, query_vault, query_with_threshold, get_session_context, get_journal, and 71 more. Their descriptions and schemas cost roughly 10,415 tokens of context every time the server is loaded.

Does the VaultCrux Platform MCP server require authentication?

Its publisher declares that VaultCrux Platform requires credentials, so you will need to authorise it in your MCP client. We have not been able to confirm that against the live endpoint.

Is the VaultCrux Platform MCP server still maintained?

VaultCrux Platform has been unreachable for long enough that we treat it as dead, and its score is pinned to zero. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.