Glitchless
NPM · GLITCHLESS-MCP
Game observability for coding agents: stutter, crashes, where players quit, and playtest bots.
Available components
Last scanned (2 hours ago)
Scores higher than 38% of npm servers
Category Monitoring and Observability
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
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- 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 (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability62
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2718 tokens (~209/item across 13 items; 13 tools + 0 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 Management7
- Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 98% 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 14 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
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.
- 23 Oct 26 +26
- Malware scan: unverified → pass ▲ security
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.86 ▲ functional
- 22 Oct 26 −12
- Known CVEs: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Malware scan: unverified → pass ▲ security
- Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
- Schema quality: 144 → 209 ▼ functional
- Dependency health: 0.85 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Stability: unverified → 0.03 ▲ functional
- First check of Schema quality: unverified functional
- Package version: 0.1.1 → 0.2.0 functional
- Package version: 0.1.1 → 0.1.2 functional
- 21 Oct 26 54
First indexed and scored.
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 23 Oct 2026 · Analysed npm/glitchless-mcp@0.2.0
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 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
glitchless_compare_versions ~218
Compare game versions side by side, in the game's own terms first: the stats on its boards (glitchless_dashboard) and its own events per session, then the built-in measures it reports (frame time overall and per level, hitches/min, crash-free and error-free sessions, errors per session, level completion, rage-quit rate, deaths per session, geometry growth). Use it to confirm a fix or a design change after shipping a new version.
| Name | Type | Req | Description |
|---|---|---|---|
| a | string | – | Baseline version (default: second newest) |
| b | string | – | New version (default: newest) |
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| service | string | – | Game service name (defaults to the most recently active game) |
No output schema declared.
No examples provided.
glitchless_dashboard ~240
The game's dashboard: its pages in order, each a board (panels in the game's own terms) or a built-in view (events, performance, errors, players, heatmaps, sessions, versions, live), and one board's panels with their numbers for the window. `page` picks the board (default: the first). `source` says whether the dashboard was saved (by an agent or a person) or made automatically from what the game sends; `spec` is what to edit and send back to glitchless_set_dashboard.
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| page | string | – | Id of the board page to evaluate (default: the first board) |
| service | string | – | Game service name (defaults to the most recently active game) |
| version | string | – | Only include sessions from this game version |
No output schema declared.
No examples provided.
glitchless_death_hotspots ~188
Where players die on a level: clustered death positions in world coordinates (x range, share of the level’s deaths, top cause, rage quits at that spot), plus the level bounds and completion stats. Use it to find difficulty spikes, then look up the level data around those coordinates.
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| level | string | yes | Level id, e.g. "level-3" |
| service | string | – | Game service name (defaults to the most recently active game) |
| version | string | – | Only include sessions from this game version |
No output schema declared.
No examples provided.
glitchless_events ~249
The game's own metrics, from the custom events it sends with track(): each event's count in the window, the sessions and players that sent it, and how its attribute values break down (for example plays by mode, paywall views by placement, purchases started vs done). Give `funnel` to count the sessions that went from one event to the next, in that order.
| Name | Type | Req | Description |
|---|---|---|---|
| funnel | string | – | Steps in order, comma-separated: "open,paywall,buy". A step can require a value: "buy=done" (any attribute) or "buy:step=done" |
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| name | string | – | Only this event, e.g. "paywall" |
| service | string | – | Game service name (defaults to the most recently active game) |
| version | string | – | Only include sessions from this game version |
No output schema declared.
No examples provided.
glitchless_get_error ~182
Error Tracking for a game. Without a fingerprint: the list of error issues ranked by sessions affected. With a fingerprint: the full issue — message, location, stack trace, affected levels/versions, occurrence counts and breadcrumbs (the game events right before it fired).
| Name | Type | Req | Description |
|---|---|---|---|
| fingerprint | string | – | Issue fingerprint from the list or from glitchless_triage |
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| service | string | – | Game service name (defaults to the most recently active game) |
| version | string | – | Only include sessions from this game version |
No output schema declared.
No examples provided.
glitchless_list_games ~31
List the games reporting to Glitchless, with their versions, environments and when they were last seen.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
glitchless_overview ~156
Headline KPIs for a game: sessions, players, crash-free and error-free sessions, frame-time p50/p95/p99 vs budget, hitches per minute, rage quits, top errors and the level funnel.
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| service | string | – | Game service name (defaults to the most recently active game) |
| version | string | – | Only include sessions from this game version |
No output schema declared.
No examples provided.
glitchless_performance ~219
Frame-time breakdown for a game: global percentiles vs the frame budget, per-level p50/p95/p99 with draw calls / triangles / geometry counts / game-context gauges, hitch causes (script, shader compile, GC, asset load), what is on screen during hitches, which events precede hitches, per GPU tier / browser / version, memory growth per level load and the slowest recent hitches with script attribution.
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| level | string | – | Focus on one level id, e.g. "level-2" |
| service | string | – | Game service name (defaults to the most recently active game) |
| version | string | – | Only include sessions from this game version |
No output schema declared.
No examples provided.
glitchless_player_funnel ~158
Player experience per level: sessions that started vs completed each level, attempts, deaths per session and their causes, average clear time, rage quits (quit ≤20s after dying), session length distribution and recent rage quits with positions.
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| service | string | – | Game service name (defaults to the most recently active game) |
| version | string | – | Only include sessions from this game version |
No output schema declared.
No examples provided.
glitchless_playtest ~237
Playtest the game with its autoplay bots and compare against a saved baseline. Bots play fixed-seed scenarios in real Chrome, one at a time, against the running game; Glitchless then compares frame time (overall and per level), render CPU, draw calls, errors, crashes, completion and deaths with the baseline. Regressions fail; warnings and improvements are listed. Call with save_as "baseline" BEFORE changing code, then without arguments AFTER the change. Takes 1–5 minutes (quick: about 1). Needs the game and the Glitchless server running and Playwright installed in the project.
| Name | Type | Req | Description |
|---|---|---|---|
| compare_to | string | – | Saved run to compare with (default "baseline" when saved) |
| game_url | string | – | Game URL to play (default http://localhost:5173/ or glitchless.playtest.json) |
| max_seconds | number | – | Cap each run at this many seconds |
| quick | boolean | – | Play only the first scenario (about a minute) |
| save_as | string | – | Save this run under a name, e.g. "baseline" before a change |
No output schema declared.
No examples provided.
glitchless_session ~102
One play session in detail: device/GPU, outcome (crashed, rage quit), and the full event timeline (levels, deaths with positions, errors, hitches with causes, agent annotations) plus per-5s frame stats. Use with session ids from errors, hitches or rage quits.
| Name | Type | Req | Description |
|---|---|---|---|
| service | string | – | Game service name (defaults to the most recently active game) |
| session_id | string | yes | Session id (s_…) |
No output schema declared.
No examples provided.
glitchless_set_dashboard ~271
Save the game's dashboard: its pages, in the order the sidebar shows them. Each page is a board of panels in the game's own words, or a built-in view (events, performance, errors, players, heatmaps, sessions, versions, live) the game keeps, renames or drops. Design it for this game, not for a genre it isn't: a puzzle game cares about solve time and hints, a mobile game about opens, modes, the paywall and purchases, a platformer about deaths per level. The first page opens first. Use the events the game sends (glitchless_events lists them, with their attributes); on a board, stats first, then the game's own events and funnels, then levels, frame_time and errors. Leave out what the game has no data for (no Heatmaps page for a game without positions). Send every page: read the current ones with glitchless_dashboard (its spec), change them, send them all back. Pass reset: true to go back to the automatic dashboard. Needs a secret key with the dashboard scope.
| Name | Type | Req | Description |
|---|---|---|---|
| pages | array | – | – |
| reset | boolean | – | Delete the saved dashboard and go back to the automatic one |
| service | string | – | Game service name (defaults to the most recently active game) |
No output schema declared.
No examples provided.
glitchless_triage ~177
Ranked findings for a game: performance spikes per level (with the gauges and events they correlate with), memory leaks, top errors, difficulty spikes / rage-quit hotspots and version regressions — ranked by severity and player impact, each with evidence and a suggested fix. Start here when asked 'what's wrong with my game?'.
| Name | Type | Req | Description |
|---|---|---|---|
| hours | number | – | Look-back window in hours (default 24). Up to the plan's retention on Glitchless Cloud: 336 (14 days) on Free, 2160 (90 days) on Indie, 9600 (400 days) on Studio. Past 744 (31 days) answers are by da… |
| service | string | – | Game service name (defaults to the most recently active game) |
| version | string | – | Only include sessions from this game version |
No output schema declared.
No examples provided.
How do I install the Glitchless MCP server?
Glitchless runs locally as an npm package, launched with npx -y glitchless-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 · glitchless-mcp
claude mcp add glitchless-gg-glitchless -- npx -y glitchless-mcp
What is the Glitchless MCP server?
Glitchless is an MCP server listed in the public MCP registry as io.github.glitchless-gg/glitchless. Game observability for coding agents: stutter, crashes, where players quit, and playtest bots. This page covers its npm package (glitchless-mcp).
Is the Glitchless MCP server safe to use?
Glitchless scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 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 Glitchless MCP server expose?
Glitchless exposes 13 tools: glitchless_list_games, glitchless_triage, glitchless_overview, glitchless_performance, glitchless_get_error, and 8 more. Their descriptions and schemas cost roughly 2,428 tokens of context every time the server is loaded.
Is the Glitchless MCP server still maintained?
Glitchless is still listed as active in the MCP registry. We last reached this channel on 23 October 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 Glitchless MCP server under?
Glitchless declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.