Skip to content
Back to search
100
MCP live MCP 2025-06-18 streamable-http

Boosthis

com.boosthis/boosthis

Read-only performance insights for your Boosthis projects: speed, crashes, traces, and fixes.

Uptime
100.0%
1 direct probes · 30d
Response
1470ms
last probe
Tools
25
callable
Resources
0
readable
Prompts
0
available

Tools · 25

boosthis_list_rules

Every Boosthis performance rule available to this runtime, as ids and titles. It is the index for boosthis_get_rule.

boosthis_get_rule

Full detail for one rule: title, when_to_apply, evidence, and — for a registered project — the prescriptive fix_template. fix_available: false means no fix text is served here, and fix_note says what …

boosthis_get_integration_kit

A Boosthis kit for THIS project — no upload; the single-use address needs no key, include_files no shell. Withheld reply? Same kit at GET https://www.boosthis.com/api/kit/<runtime> (project key as bea…

boosthis_get_removal_kit

Everything involved in removing Boosthis from this project: the removal sequence, every kit file, the package entries, the config file, the calls to strip, and the Boosthis entries in an AI tool's con…

boosthis_match_rules_for_code

Ranks Boosthis rules against a code snippet using each rule's id tokens and when_to_apply text, up to 8 candidates. They are ranked guesses from a text match, not findings: each rule's when_to_apply i…

boosthis_check_for_update

Whether a newer Boosthis kit exists for this project, without fetching it: latest_version, update_available, comparison (behind/current/ahead/unknown), the changelog for every release behind, a severi…

boosthis_verify_kit

Tamper-evidence check: re-hashes every vendored Boosthis-owned file against the shipped manifest. 'ok' when every file matches, 'mismatch' when one changed, went missing or was added. A mismatch matte…

boosthis_session_summary

Per-screen p50/p75/p95 and worst rating, worst screens first, with p99, spike ratio and stdev spread where the server has them. Without read credentials the answer is a note pointing at the dashboard,…

boosthis_recent_samples

The most recent per-screen performance samples, newest first, optionally filtered to one screen. Without read credentials the answer is a note pointing at the dashboard, never an empty result. Read-on…

boosthis_budgets

The auto-learned baseline (older p95) against the recent p95 for each screen, and which screens regressed. Without read credentials the answer is a note pointing at the dashboard, never an empty resul…

boosthis_what_should_i_look_at_next

A triage ordering: the worst-rated and slowest screens first, each with a one-line reason. Without read credentials the answer is a note pointing at the dashboard, never an empty result. Read-only. Ot…

boosthis_snapshot

The whole Boosthis bubble for one install — the latest upload: boot ladder, frame meters (Speed / Smoothness / Scroll / Stability / Render), Frustration and Idle axes, per-route rows, per-screen diagn…

boosthis_crash_risk

The crash classes this app has already recorded — uncaught errors, unhandled rejections and caught render near-misses — newest first, each with an error name, a redacted top frame, an occurrence bucke…

boosthis_full_stack_trace

One user action stitched across the stack as a waterfall of spans — layer, code-defined route label, duration, start offset, rating — plus a full-stack score against the shared TTI thresholds, a summa…

boosthis_connection_status

What Boosthis knows about this account's installs (same check over plain HTTPS: GET /api/connection-status, project key as bearer): for each, the runtime, the state it is in, when it was last heard fr…

boosthis_verify_kit_install

Check a Boosthis kit's FILES ON DISK are byte-perfect (same check over plain HTTPS: POST https://www.boosthis.com/api/kit/<runtime>/verify) — a pass proves the files, never that anything is measured y…

boosthis_maintenance_mix

The Maintenance Mix: of the issues a project actually fixed, how many were fixed before users felt them (flagged by a Boosthis rule, app still healthy) versus after a crash or a visible poor rating. w…

boosthis_trend

One project's last 30 days: for each finished day, how many measurements arrived, the typical and worst-case screen time, how many were rated poor, new crashes, and alerts opened and closed — plus a p…

boosthis_vigilance

One project's standing Vigilance verdict and every watch behind it, worst first: what each watches, what it says now, and the evidence (how many measurements, over which window, on which part, when th…

boosthis_jobs

Every scheduled job this project reports, each in one state: on time; late; app unheard, meaning reporting stopped before the run was due, so the job is not blamed; never reported a run; or no rhythm …

boosthis_alerts

This account's Boosthis alerts in the same words the dashboard uses. Each is Open, Read, Fixed, Returned (marked fixed and then happened again) or Dismissed, and says whether its screen or check is Mu…

boosthis_promises

The standing promises this project's developer has recorded — what they want kept as the project changes. They survive from earlier sessions and earlier assistants. Each says whether Boosthis can meas…

boosthis_remember_promise

Saves something the developer wants kept true from now on — a screen that has to stay fast, a problem that must not come back, a rhythm that has to hold — as a promise on the project, in their words, …

boosthis_check_claim

Holds a sentence an assistant is about to say against what the running app actually did. Exactly one of four answers: supported, not supported by the measurements, cannot tell yet, or outside what Boo…

boosthis_release_check

How the last release held up, from the running app after it shipped. Against the version this project's own measurements reported, five separate answers: did the problems it had handed a fix for stop,…

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "boosthis": {
      "url": "https://www.boosthis.com/mcp",
      "transport": "streamable-http"
    }
  }
}