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.

Trackly CLI

NPM · TRACKLY-CLI · 2 COMPONENTS

Search Thousands of jobs, Thousands of companies. MCP for Claude, ChatGPT, Codex and Cursor.

−11 this week 82 Trust /100

Last scanned (7 hours ago)

Scores higher than 72% of npm servers

Category CRM and Sales

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 Security63
  • No malware found by supply-chain analysis.Pass
  • Known CVEs could not be checked: the version this server declares is not published in its registry.Unverified
  • No install/post-install scripts declared.Pass
  • Dependency health could not be checked: the version this server declares is not published in its registry.Unverified
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to trackly-app/trackly-cli). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability76
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 8611 tokens (~145/item across 59 items; 58 tools + 1 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 Management97
  • Stability check failed: the tool surface changed between 0.18.6 and 0.25.0: 0 tool removals, 3 breaking changes, 0 additions. See how to fix → Fail
Tool Coverage77
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 32% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 58 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 59 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
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.

  • 5 Nov 26 −11
    • Stability: fail → unverified ▼ security
    • Known CVEs: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: 100 → unverified ▼ functional
    • Dependency health: 0.88 → unverified ▼ functional
    • Package version: 0.24.0 → 0.25.0 functional
  • 4 Nov 26 +11
    • Known CVEs: unverified → pass ▲ security
    • Dependency health: unverified → 0.88 ▲ functional
  • 3 Nov 26 −11
    • Known CVEs: pass → unverified ▼ security
    • Dependency health: 0.88 → unverified ▼ functional
    • Package version: 0.23.0 → 0.24.0 functional
  • 29 Oct 26 +15
    • Stability: fail → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Tool coverage: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Schema quality: 100 → unverified ▼ functional
    • Package version: 0.22.3 → 0.23.0 functional
  • 28 Oct 26 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 0.22.2 → 0.22.3 functional
  • 26 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 91 to 94.

  • 25 Oct 26 +14
    • Malware scan: unverified → pass ▲ security
  • 24 Oct 26 −12
    • CVE-2026-110095 affects this package: high ▼ security
    • CVE-2026-110306 affects this package: high ▼ security
    • CVE-2023-54404 affects this package: high ▼ security
    • CVE-2026-110725 affects this package: high ▼ security
    • CVE-2026-110180 affects this package: high ▼ security
    • Malware scan: pass → unverified ▼ security
    • CVE-2026-109955 no longer affects this package ▲ security
    • CVE-2026-111997 no longer affects this package ▲ security
    • Known CVEs: fail → pass ▲ security
    • Package version: 0.22.1 → 0.22.2 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 5 Nov 2026 · Analysed npm/trackly-cli@0.25.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo trackly-app/trackly-cli
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/trackly-app/trackly-cli/.github/workflows/publish.yml@refs/heads/main
Rekor log index 3692559617
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:4e4721bd215eede80ce08a58456a3282fdc92f3bd67c26c3f4a1508b7d453fd0e5d0d30021b8f7b2599dc0e490bd27267006847abc35fb6d823957f6e

Background: How many MCP packages publish verified provenance →

MCP tools · 58 exposed · ~8,594 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
trackly_start_apply_run ~148

Start a legacy single run, or start/recover a frozen member when the complete batch binding is supplied. Recovered members already carrying runId must reuse that run without calling this tool.

NameTypeReqDescription
batchIdinteger––
clientNamestring––
contextstring–Briefly explain why this tool helps the current job-search goal. Never include resume text, profile answers, demographic or work-authorization answers, application notes, credentials, or secrets.
expectedInspectionEpochinteger––
expectedMemberVersioninteger––
jobIdintegeryes–
leaseTokenstring––
memberIdinteger––

No output schema declared.

No examples provided.

trackly_stop_apply_execution ~101

Stop the active execution without changing saved-job state or submitting any application.

NameTypeReqDescription
contextstring–Briefly explain why this tool helps the current job-search goal. Never include resume text, profile answers, demographic or work-authorization answers, application notes, credentials, or secrets.
executionIdintegeryes–
expectedRevisionintegeryes–
idempotencyKeystringyes–
reasonCodestring––

No output schema declared.

No examples provided.

trackly_update_application_profile ~189

Update confirmed profile answers with optimistic concurrency. Use global scope only for an explicit always-answer preference. Setting sensitiveStorageConsent=false deletes every stored sensitive and restricted answer (an admin-recoverable archive is kept for 30 days, then purged) and is a two-step action: the first call saves nothing and returns a confirmation challenge; retry with the echoed sensitiveRevocationConfirmToken to proceed.

NameTypeReqDescription
changesarray––
confirmProfileboolean––
contextstring–Briefly explain why this tool helps the current job-search goal. Never include resume text, profile answers, demographic or work-authorization answers, application notes, credentials, or secrets.
educationarray––
expectedRevisionintegeryes–
sensitiveRevocationConfirmTokenstring––
sensitiveStorageConsentboolean––
sourcestring––

No output schema declared.

No examples provided.

trackly_update_experience_limits ~244

Atomically replace the complete role-specific experience-limit map. Each value is the highest stated minimum years requirement the user wants for that job function. When Trackly enforcement is active, a job is included when its stated minimum is less than or equal to the limit. Jobs with no stated minimum remain visible. An empty object clears the saved limits. experienceFilterV2Available reports edit capability, not enforcement state. Read discoveryPreferenceRevision with trackly_get_preferences first. If the backend returns a revision conflict, refetch and reconcile with the user; never retry blindly with the newer revision.

NameTypeReqDescription
contextstring–Briefly explain why this tool helps the current job-search goal. Never include resume text, profile answers, demographic or work-authorization answers, application notes, credentials, or secrets.
expectedPreferenceRevisionintegeryesThe non-negative safe-integer discoveryPreferenceRevision returned by the latest trackly_get_preferences call. A stale revision is rejected instead of overwriting newer choices.
experienceLimitsByJobFunctionobjectyesComplete replacement map from canonical job-function slug to maximum acceptable stated minimum years. Use {} to turn role-specific experience filtering off.

No output schema declared.

No examples provided.

trackly_update_status ~84

Update a job application status (apply, save, or dismiss).

NameTypeReqDescription
actionstringyesStatus action
contextstring–Briefly explain why this tool helps the current job-search goal. Never include resume text, profile answers, demographic or work-authorization answers, application notes, credentials, or secrets.
idnumberyesJob posting ID

No output schema declared.

No examples provided.

trackly_validate_apply_resume_upload ~163

Locally validate the browser adapter capabilities and ordered, value-free proof stages required to claim one resume attachment. Set capabilities.directFileSet=true only for documented exact-input file setting: semantic_control_discovered -> set_files_succeeded -> user_facing_filename_committed -> parser_fields_rechecked, without chooser events. Otherwise require chooserArming and both chooser stages. This helper does not open a chooser, read a local path, control the browser, or send values to Trackly.

NameTypeReqDescription
capabilitiesobjectyes–
contextstring–Briefly explain why this tool helps the current job-search goal. Never include resume text, profile answers, demographic or work-authorization answers, application notes, credentials, or secrets.
eventsarrayyes–

No output schema declared.

No examples provided.

trackly_validate_apply_tab_keep_set ~138

Locally validate a caller-supplied session-finalizer keep set against complete controller and user tab inventories. This pure helper never enumerates, focuses, closes, hands off, or finalizes browser tabs and never sends tab IDs to Trackly.

NameTypeReqDescription
contextstring–Briefly explain why this tool helps the current job-search goal. Never include resume text, profile answers, demographic or work-authorization answers, application notes, credentials, or secrets.
controllerInventoryobjectyes–
expectedTabIdsarrayyes–
keepTabIdsarrayyes–
userInventoryobjectyes–

No output schema declared.

No examples provided.

trackly_verify_prepared_resume ~136

Immediately before attachment, recompute the prepared resume fingerprint, validate its run and expiration, and lock the confirmed file read-only.

NameTypeReqDescription
confirmationIdstringyes–
contextstring–Briefly explain why this tool helps the current job-search goal. Never include resume text, profile answers, demographic or work-authorization answers, application notes, credentials, or secrets.
exactLocalPathstringyes–
expiresAtstringyes–
resumeIdintegeryes–
runIdintegeryes–
sha256stringyes–
sizeBytesintegeryes–

No output schema declared.

No examples provided.

Install

How do I install the Trackly CLI MCP server?

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

npm · trackly-cli

# add to Claude Code
claude mcp add trackly-app-trackly -- npx -y trackly-cli
Common questions

What is the Trackly CLI MCP server?

Trackly CLI is an MCP server listed in the public MCP registry as io.github.trackly-app/trackly. Search Thousands of jobs, Thousands of companies. MCP for Claude, ChatGPT, Codex and Cursor. This page covers its npm package (trackly-cli).

Is the Trackly CLI MCP server safe to use?

Trackly CLI scores 82 out of 100 on VerifyMCP. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Trackly CLI MCP server expose?

Trackly CLI exposes 58 tools: trackly_search_jobs, trackly_get_job, trackly_search_companies, trackly_list_companies, trackly_get_stats, and 53 more. Their descriptions and schemas cost roughly 8,594 tokens of context every time the server is loaded.

Is the Trackly CLI MCP server still maintained?

Trackly CLI is still listed as active in the MCP registry. We last reached this channel on 5 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 Trackly CLI MCP server under?

Trackly CLI declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.