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.

Vestige

NPM · VESTIGE-MCP-SERVER

Causal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause.

Available components

+1 this week 82 Trust /100

Last scanned (22 hours ago)

Scores higher than 71% of npm servers

Category Memory and Knowledge

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 5 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (AGPL-3.0-only).Pass
  • Actively maintained (last published 28 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability68
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Context-footprint check failed: tool/resource definitions use about 2928 tokens (~108/item across 27 items; 16 tools + 11 resources), over budget; trim descriptions and params. See how to fix → Fail
  • 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 Coverage74
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 7% of tool parameters carry a description.Partial
  • Structured output schemas are declared (25% 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 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (17)

  • 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
  • Capabilities

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.

  • 15 Nov 26 +1
    • Stability: 0.97 → pass security
  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

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/vestige-mcp-server@4.2.0

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 →

Dependencies 5 packages
Packages resolved 5
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 16 exposed · ~2,482 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
causal_walk ~120

Walk a failure backward from explicit start points (failing_test, stack_frame, ci_run, logged_write, version_range); any kind carries node_id, the memory recording the symptom. A Strata log follows recorded causal edges only and says why when none lead upstream. Results are hypotheses, not proven causes. promote=true records trail edges on the legacy engine only.

NameTypeReqDescription
lookback_daysinteger––
promoteboolean––
scan_limitinteger––
scopestring––
start_pointsarray––

No output schema declared.

No examples provided.

codebase ~235

Code memory. Actions: 'remember_pattern', 'remember_decision', 'get_context' (patterns and decisions marked current or stale, and the scopes holding them), 'verify' (re-check anchors and, with a codebase, change records), 'reanchor' (replace reviewed evidence), 'ingest_repo' (a checkout's commits as anchored change records; previews unless dryRun=false).

NameTypeReqDescription
actionstringyesSave, list, and re-check code knowledge.
allScopesboolean––
alternativesarray––
anchorsarray––
codebasestring––
decisionstring––
descriptionstring––
dryRunboolean––
filesarray––
limitinteger––
memoryIdstring––
namestring––
rationalestring––
repoPathstring––
revstring––
scopestring––
sincestring––
untilstring––
verifyboolean––

No output schema declared.

No examples provided.

dedup ~275

Duplicates and exact tag maintenance. Actions: scan (default, read-only), plan_merge, plan_supersede, apply (confirm=true), undo, tag_rename, tag_merge (preview-token gated), protect, policy. Merges invalidate, never delete. Withheld on Strata in 4.0: plan_merge, plan_supersede, apply, verdict, protect.

NameTypeReqDescription
actionstring–'scan' (default, read-only): exact-equality
all_scopesboolean––
auto_applyboolean––
confirmboolean––
idstring––
limitinteger––
match_thresholdnumber––
member_idsarray––
new_idstring––
old_idstring––
operation_idstring––
plan_idstring––
possible_thresholdnumber––
preview_tokenstring––
protectedboolean––
reasonstring––
scopestring––
source_tagstring––
source_tagsarray––
survivor_idstring––
tagsarray––
target_tagstring––
verdictstring––

No output schema declared.

No examples provided.

forgotten_lesson ~50

Earlier memories on recorded causal edges from a failure, lowest FSRS retrievability first.

NameTypeReqDescription
failure_idstringyes–
scan_limitinteger––
scopestring––

No output schema declared.

No examples provided.

ghostlink ~234

Never-composed memory pairs, each with its proof from recorded edges only. Modes: propose (lens bridge|divergent), bounty, weave (write), map, inspect, explore, predict, harden (write).

NameTypeReqDescription
center_idstring––
contextobject––
cursorstring––
depthinteger––
event_idstring––
evidencearray––
first_idstring––
fromstring––
includeCrossScopeboolean––
kindstring––
lensstring––
limitinteger––
max_nodesinteger––
memory_idstring––
modestringyespropose: never-composed pairs with proofs (lens
outcome_typestring––
querystring––
scopestring––
second_idstring––
tagsarray––
tostring––
viewstring–[inspect] Which composition view to read.

No output schema declared.

No examples provided.

intention ~184

Intentions. Actions: 'set', 'check', 'update', 'list'; 'graph' evaluates evidence-aware plans through a nested command. A trigger fires on a clock or on exact equality with a handle in the check context; descriptions are never parsed.

NameTypeReqDescription
actionstringyes'set' creates, 'check' finds triggered, 'update'
atstring––
commandobject––
contextobject––
deadlinestring––
descriptionstring––
filter_statusstring––
idstring––
include_snoozedboolean––
limitinteger––
prioritystring––
scopestring––
snooze_minutesinteger––
statusstring––
triggerobject––

No output schema declared.

No examples provided.

maintain ~244

Lifecycle: 'consolidate', 'dream', 'dream_compile', 'gc' (dry run default), 'importance_score', 'backup', 'export', 'restore'. Withheld on Strata in 4.0: consolidate, restore.

NameTypeReqDescription
actionstringyes–
afterstring––
allowAnyPathboolean––
batchSizeinteger––
budgetMsinteger––
contentstring––
context_topicsarray––
dry_runboolean––
filtersobject–Optional filters, grouped.
formatstring––
idstring––
max_age_daysinteger––
max_pairsinteger––
max_prsinteger––
memory_countinteger––
mergeboolean––
min_retentionnumber––
min_similaritynumber––
pathstring––
phasestring––
projectstring––
scopestring––
sincestring––
tagsarray––

No output schema declared.

No examples provided.

memory ~166

Manage one memory: 'get', 'get_batch', 'state', 'promote' / 'demote' (demote never deletes), 'edit' (admit a successor, retire the previous node). Erasure is withheld on Strata in 4.0.

NameTypeReqDescription
actionstringyes'get', 'get_batch' (ids), 'state', 'promote' / 'demote' (demote never deletes), 'edit' (admit a successor, retire the previous node). Erasure is withheld on Strata in 4.0.
confirmboolean––
contentstring––
idstring––
idsarray––
reasonstring––
rolestring––

No output schema declared.

No examples provided.

memory_status ~185

Store status. Views: 'health' (default), 'retention', 'timeline' (memories by day), 'changelog' (state-change audit trail), 'provenance' (memoryId), 'coverage', 'stats' (counts by type, tag, age, retention), 'tools' (advertised tools and actions; pass tool for one schema).

NameTypeReqDescription
all_scopesboolean––
detail_levelstring––
endstring––
limitinteger––
memory_idstring––
node_typestring––
schema_introspectionboolean––
scopestring––
startstring––
tagsarray––
toolstring––
viewstring–'tools': current tool/action inventory, or one
NameTypeReqDescription
viewstring––

No examples provided.

project ~139

Project the durable subset of a scope (decisions, patterns, rule-tagged facts) into a fenced region of CLAUDE.md or MEMORY.md, one memory id per line. 'preview' (default) shows the diff; 'write' needs confirm=true and replaces only the fence.

NameTypeReqDescription
actionstring–'preview' (default) renders and diffs, writes
confirmboolean––
filtersobject–Optional filters, grouped.
formatstring––
max_itemsinteger––
pathstring––
rootstring––
scopestring––

No output schema declared.

No examples provided.

recall ~209

Find memories by exact handle: a full memory id or an exact tag; a unique id prefix of 8+ characters also resolves. Free text and the 'reason' / 'contradictions' modes return similarity_disabled.

NameTypeReqDescription
abstain_floornumber––
context_topicsarray––
depthinteger––
detail_levelstring––
filtersobject–Optional filters, grouped.
handlestring––
includeCrossScopeboolean––
include_supersededboolean––
limitinteger––
min_trustnumber––
modestring–'lookup' (default): by handle. 'reason' and 'contradictions' return similarity_disabled in 4.0.
querystring––
scopestring––
sincestring––
sourceobject–Optional filters, grouped.
topicstring––
NameTypeReqDescription
querystring––
resultsarray––

No examples provided.

receipt ~76

'get' shows what a write did from its receipt id; 'replay' re-derives that state from the log and reports any mismatch.

NameTypeReqDescription
actionstringyes–
paramsobject––
receipt_idstring––
remove_edgestring––
withheld_slotsarray––
NameTypeReqDescription
receiptIdstring––
retrievedarray––

No examples provided.

selftest ~29

Planted-cause selftest: walks recorded edges back to a planted cause in a throwaway log.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

session_start ~93

Start-of-session context in one call: open intentions, status and code memories under one token budget.

NameTypeReqDescription
changed_filesarray––
contextobject––
filtersobject–Optional filters, grouped.
include_intentionsboolean––
include_predictionsboolean––
include_statusboolean––
queriesarray––
scopestring––

No output schema declared.

No examples provided.

smart_ingest ~168

Save one memory ('content') or up to 20 ('items'); each write passes the gate and returns a receipt. Secret-shaped content is refused unless allowSecrets is set.

NameTypeReqDescription
acceptedTagSuggestionsobject––
allowSecretsboolean––
batchMergePolicystring––
contentstring––
forceCreateboolean––
intent_idstring––
itemsarray––
linksarray––
node_typestring––
previewTagSuggestionsboolean––
rolestring––
scopestring––
sourcestring––
tagsarray––
validFromstring––
validUntilstring––
NameTypeReqDescription
decisionstring––
nodeIdstring––

No examples provided.

suppress ~75

Hide a memory from every read; the log keeps its bytes. On Strata in 4.0 it cannot be undone (reverse=true is refused) and is not erasure.

NameTypeReqDescription
cascade_derived_fromboolean––
idstringyes–
reasonstring––
reverseboolean––

No output schema declared.

No examples provided.

Install

How do I install the Vestige MCP server?

Vestige runs locally as an npm package, launched with npx -y vestige-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 · vestige-mcp-server

# add to Claude Code
claude mcp add samvallad33-vestige -- npx -y vestige-mcp-server
Common questions

What is the Vestige MCP server?

Vestige is an MCP server listed in the public MCP registry as io.github.samvallad33/vestige. Causal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause. This page covers its npm package (vestige-mcp-server).

Is the Vestige MCP server safe to use?

Vestige scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 Vestige MCP server expose?

Vestige exposes 16 tools: causal_walk, codebase, dedup, forgotten_lesson, ghostlink, and 11 more. Their descriptions and schemas cost roughly 2,482 tokens of context every time the server is loaded.

Is the Vestige MCP server still maintained?

Vestige 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 Vestige MCP server under?

Vestige declares the AGPL-3.0-only 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 Vestige MCP server?

VerifyMCP ran 17 checks on Vestige, covering Malware scan, Known CVEs, Install scripts, Dependency health and 13 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.