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.Apertur3/headroom

NPM · HEADROOMD

Live subscription limits, resets and budget checks for coding agents over MCP.

Available components

+3 this week 82 Trust /100

Last scanned (1 hour ago)

Scores higher than 72% of npm servers

Category CI/CD and DevOps

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
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to Apertur3/headroom). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 1 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability55
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 1240 tokens (~72/item across 17 items; 17 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management60
  • Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.

  • 4 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.

  • 3 Nov 26 +31
    • Injection markers: unverified → pass ▲ security
    • MCP protocol: unverified → fail ▼ functional
    • Tool coverage: unverified → 100 ▲ functional
    • Stability: unverified → 0.53 ▲ functional
    • Package version: 0.2.18 → 0.2.20 functional
    • Package version: 0.2.18 → 0.2.19 functional
  • 2 Nov 26 −30
    • Tool safety: pass → unverified ▼ security
    • Stability: 0.47 → unverified ▼ security
    • Capabilities: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Package version: 0.2.17 → 0.2.18 functional
  • 31 Oct 26 +1
    • Package version: 0.2.15 → 0.2.17 functional
    • Package version: 0.2.15 → 0.2.16 functional
    • Package version: 0.2.14 → 0.2.15 functional
  • 29 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 27 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 25 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 24 Oct 26 0
    • Package version: 0.2.14 → 0.2.15 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/headroomd@0.2.20

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 Apertur3/headroom
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/Apertur3/headroom/.github/workflows/release.yml@refs/tags/v0.2.20
Rekor log index 3673811865
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:577ab985621f4d02a753efb19884479d2b8ae7988f7be29a006e1dc8d6f6c6c8a01cb2f3af6164f24d2a23df30d7586d5d8482381385f4074346208c4

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 17 exposed · ~1,240 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
quota_can ~96

Check whether an action class can consume all of its meters. With no expect_percent, reports the learned cost and confidence for this action class; lease atomically reserves every consumed meter for the learned (or given) expectation so the next call learns too.

NameTypeReqDescription
action_classstringyes–
allow_unknownboolean––
expect_percentnumber––
leaseboolean––
ownerstringyes–

No output schema declared.

No examples provided.

quota_cost ~34

Learned median, interquartile range and sample count of spent percent, per action class.

NameTypeReqDescription
action_classstring––

No output schema declared.

No examples provided.

quota_events ~30

Return Headroom events since an ISO timestamp or duration resolved by the caller.

NameTypeReqDescription
sincestring––

No output schema declared.

No examples provided.

quota_fill ~98

How many more lanes fit before a vendor-reported window resets. need selects that window.

NameTypeReqDescription
action_classstring––
allowancestring––
duration_minutesnumber––
lane_cost_percentnumber––
meterstringyes–
needstring––
ownerstring––
plan_share_percentnumber––
weekly_reserve_percentnumber––

No output schema declared.

No examples provided.

quota_gate ~125

Pre-dispatch check for vendor-reported windows. needs accepts 5h, wk, 30d, or an exact <n>m, <n>h, or <n>d duration.

NameTypeReqDescription
action_classstring––
allowancestring––
cap_percentnumber––
duration_minutesnumber––
meterstring––
needsarrayyes–
ownerstring––
planboolean––
plan_share_percentnumber––
reserve_percentnumber––

No output schema declared.

No examples provided.

quota_heartbeat ~155

Record or refresh this orchestrator's heartbeat lease with the daemon -- the one process that survives a crashed session -- so a lapse past 2x interval_ms is noticed and, once configured, notified. owner defaults to this MCP session's client name and session id, same as quota_lease_start. resume_sentence is what a human or a fresh session should do to pick this session's work back up; omit it on a plain re-beat to keep whatever was registered before. Pass stop: true to deregister instead of beating (interval_ms and resume_sentence are ignored then).

NameTypeReqDescription
interval_msnumber––
ownerstring––
resume_sentencestring––
stopboolean––

No output schema declared.

No examples provided.

quota_inbox ~66

Read this session's hand-off messages from <HEADROOM_HOME>/inbox/<session>/, oldest first, marking each read. Read-only: sending a message is `headroom inbox send`, never this tool.

NameTypeReqDescription
sessionstringyes–
sincenumber––

No output schema declared.

No examples provided.

quota_lease_end ~70

End a meter lease. A different owner must set force plus confirm_force and a reason, both of which are audited.

NameTypeReqDescription
confirm_forceboolean––
forceboolean––
idstringyes–
ownerstringyes–
reasonstring––

No output schema declared.

No examples provided.

quota_lease_start ~79

Reserve a meter for an orchestrator. owner defaults to this MCP session's client name and session id when omitted.

NameTypeReqDescription
action_classstring––
expected_percentnumber––
meter_idstringyes–
notestring––
ownerstring––
ttl_msnumber––

No output schema declared.

No examples provided.

quota_leases ~16

List meter leases and estimated spend.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

quota_plan ~61

Points available per remaining vendor-reported window before reset, including advisory banked-reset guidance. need selects that window.

NameTypeReqDescription
meterstringyes–
needstring––
reserve_percentnumber––
target_pointsnumber––

No output schema declared.

No examples provided.

quota_rate ~55

Burn in percent per hour over the last N minutes. need selects a vendor-reported window.

NameTypeReqDescription
meterstring––
minutesnumber––
needstring––
ownerstring––

No output schema declared.

No examples provided.

quota_route ~100

Among the principals routing.toml's [consumes] entry for this action class allows, picks the one with the most remaining headroom on its own tightest window and returns its launch environment (e.g. CLAUDE_CONFIG_DIR for a second Claude profile). Every candidate's own state and reason is reported too, not just the winner.

NameTypeReqDescription
action_classstringyes–
allow_unknownboolean––
ownerstringyes–

No output schema declared.

No examples provided.

quota_spend ~90

Per-owner attributed spend on shared meters: how much of each window's actual movement the spend ledger books to each lease owner, with a confidence. The owner `unattributed` is movement that happened while no lease was open. since is an ISO timestamp, defaulting to 24 hours ago.

NameTypeReqDescription
meterstring––
ownerstring––
sincestring––

No output schema declared.

No examples provided.

quota_status ~19

Return the latest quota windows for every Headroom meter.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

quota_usage_paste ~107

Turn the text of Claude Code's /usage panel into observations, for a meter Headroom cannot poll (a denied probe, or a model-scoped weekly bar the account-wide window hides). text is the pasted panel; principal names the Claude principal and is required when more than one is configured. Stores the readings the same way a poll does, so status, gate, can, rate and route see them immediately.

NameTypeReqDescription
principalstring––
textstringyes–

No output schema declared.

No examples provided.

quota_wait ~39

Returns immediately (never blocks) with the meter's reset time and a suggested sleep, for a caller that polls itself.

NameTypeReqDescription
meterstringyes–

No output schema declared.

No examples provided.

Install

How do I install the io.github.Apertur3/headroom MCP server?

io.github.Apertur3/headroom runs locally as an npm package, launched with npx -y headroomd. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · headroomd

# add to Claude Code
claude mcp add apertur3-headroom -- npx -y headroomd
Common questions

What is the io.github.Apertur3/headroom MCP server?

io.github.Apertur3/headroom is an MCP server listed in the public MCP registry as io.github.Apertur3/headroom. Live subscription limits, resets and budget checks for coding agents over MCP. This page covers its npm package (headroomd).

Is the io.github.Apertur3/headroom MCP server safe to use?

io.github.Apertur3/headroom scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. 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 io.github.Apertur3/headroom MCP server expose?

io.github.Apertur3/headroom exposes 17 tools: quota_status, quota_can, quota_events, quota_lease_start, quota_lease_end, and 12 more. Their descriptions and schemas cost roughly 1,240 tokens of context every time the server is loaded.

Is the io.github.Apertur3/headroom MCP server still maintained?

io.github.Apertur3/headroom 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 io.github.Apertur3/headroom MCP server under?

io.github.Apertur3/headroom declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.