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.

TruthTrail

NPM · TRUTHTRAIL

Record the decisions your AI coding agent makes, in the repo and on the Jira or GitHub ticket.

Available components

0 this week 63 Trust /100

Last scanned (15 hours ago)

Scores higher than 32% of npm servers

Category Project Management

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 Security98
  • 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
  • 31 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability73
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 758 tokens (~84/item across 9 items; 9 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage97
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 90% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "withdraw_decision" implies "withdraw" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 9 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

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.

What we tested

Checks we ran (14)

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

Checks we could not complete (2)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

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.

  • 13 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 12 Nov 26 48

    First indexed and scored.

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/truthtrail@0.4.4

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 →

Dependencies 95 packages
Packages resolved 95
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 9 exposed · ~758 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
check_branch ~41

Check this branch: ticket key, decisions and assumptions recorded, AI-assisted commits, and reminders.

NameTypeReqDescription
basestring–branch to compare against (default main)

No output schema declared.

No examples provided.

list_decisions ~38

List recorded decisions (optionally for one ticket). Read these before implementing or testing a ticket and follow them.

NameTypeReqDescription
ticketstring––

No output schema declared.

No examples provided.

list_pending ~23

Questions the user answered during this work that are not yet recorded or dismissed.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

move_decision ~68

Move a decision you recorded to the right ticket (it was recorded on a wrong one). It is withdrawn on the old ticket with 'moved to <TICKET>'.

NameTypeReqDescription
idstringyesD-12 or the long id
ticketstringyesThe right ticket key

No output schema declared.

No examples provided.

record_decision ~215

Record a product decision or assumption for the current ticket. Use it when the ticket was silent or ambiguous and the choice changes behaviour a user or QA can see, when following the ticket would break something, or when you assumed something visible (type: assumption). Not for pure implementation details.

NameTypeReqDescription
approverstring–Only if the user explicitly named who approved it. Never guess.
bodystring–Short extra explanation
chosenstringyesWhat was picked
filesarray–Files this decision affects
optionsarray–The choices that were considered
questionstringyesWhat needed deciding, e.g. 'Discount before or after tax?'
reasonstring–Why it was chosen
supersedesarray–Ids of older decisions this replaces
ticketstring–Ticket key; defaults to the key in the branch name
typestring–decision (default), assumption (you assumed it without asking), or impact

No output schema declared.

No examples provided.

resolve_pending ~202

Resolve a pending answered question: action 'record' if it changes behaviour a user or QA can see (fields override the captured values), otherwise 'dismiss'.

NameTypeReqDescription
actionstringyes–
approverstring–Only if the user explicitly named who approved it. Never guess.
bodystring–Short extra explanation
chosenstring–What was picked
filesarray–Files this decision affects
indexintegeryes–
optionsarray–The choices that were considered
questionstring–What needed deciding, e.g. 'Discount before or after tax?'
reasonstring–Why it was chosen
supersedesarray–Ids of older decisions this replaces
ticketstring–Ticket key; defaults to the key in the branch name
typestring–decision (default), assumption (you assumed it without asking), or impact

No output schema declared.

No examples provided.

set_ticket ~71

Remember which ticket this branch belongs to, when the branch name has no ticket key or the wrong one. Ask the user for the key first; never guess. Returns the ticket's title so you can check it matches the task.

NameTypeReqDescription
ticketstringyesTicket key, e.g. ABC-1234

No output schema declared.

No examples provided.

why ~45

Explain a file or line: last commit, AI or human authorship, linked decisions and the ticket.

NameTypeReqDescription
targetstringyesfile or file:line, relative to the workspace

No output schema declared.

No examples provided.

withdraw_decision ~55

Withdraw a decision you recorded (for example, recorded by mistake). Needs TruthTrail login. To change a decision, record a new one with supersedes instead.

NameTypeReqDescription
idstringyesD-12 or the long id

No output schema declared.

No examples provided.

Install

How do I install the TruthTrail MCP server?

TruthTrail runs locally as an npm package, launched with npx -y truthtrail mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · truthtrail

# add to Claude Code
claude mcp add truthtrail-truthtrail -- npx -y truthtrail mcp
Common questions

What is the TruthTrail MCP server?

TruthTrail is an MCP server listed in the public MCP registry as io.github.truthtrail/truthtrail. Record the decisions your AI coding agent makes, in the repo and on the Jira or GitHub ticket. This page covers its npm package (truthtrail).

Is the TruthTrail MCP server safe to use?

TruthTrail scores 63 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 TruthTrail MCP server expose?

TruthTrail exposes 9 tools: record_decision, list_decisions, why, check_branch, list_pending, and 4 more. Their descriptions and schemas cost roughly 758 tokens of context every time the server is loaded.

Is the TruthTrail MCP server still maintained?

TruthTrail 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 TruthTrail MCP server under?

TruthTrail 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 TruthTrail MCP server?

VerifyMCP ran 14 checks on TruthTrail, covering Malware scan, Known CVEs, Install scripts, Dependency health and 10 more. 2 items could not be completed, a gap on our side rather than a finding about TruthTrail: Security disclosure and Stability. One category scores 0 for that reason, because we only credit what we can confirm. 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.