Pincushion
NPM · PINCUSHION-MCP
Stakeholders pin feedback on your live app; your AI agent reads the pins via MCP and fixes them.
Available components
Last scanned (12 hours ago)
Scores higher than 72% of npm servers
Category Testing and QA
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 Security99
- 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 127 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency32
- 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
- Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
- Actively maintained (last published 2 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability78
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 12537 tokens (~181/item across 69 items; 67 tools + 2 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage95
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 86% 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
- All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 69 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.
- 2 Nov 26 +5
- Malware scan: pass → unverified ▼ security
- Source repository: fail → pass ▲ security
- Security disclosure: unverified → fail ▼ functional
- Package version: 1.12.1 → 1.12.5 functional
- Package version: 1.12.1 → 1.12.4 functional
- 18 Oct 26 +1
- Stability: 0.97 → pass security
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Oct 26 +43
- Injection markers: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.83 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Package version: 1.11.29 → 1.12.1 functional
- 11 Oct 26 0
- Package version: 1.12.0 → 1.12.1 functional
- 4 Oct 26 −45
- Stability: 0.97 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Stability: 0.97 → pass security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 1.11.29 → 1.12.0 functional
- 3 Oct 26 0
- Package version: 1.11.28 → 1.11.29 functional
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/pincushion-mcp@1.12.5
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 127 packages
| Packages resolved | 127 |
|---|---|
| Deprecated | 1 |
| 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 →
preview_collaboration_notification Preview Notification ~60
Preview the Slack, Teams, or Discord notification shape and recommended event routing before connecting a real webhook.
| Name | Type | Req | Description |
|---|---|---|---|
| event | string | – | Event to preview. Default: pin_ready. |
| provider | string | – | Provider payload to preview. Default: slack. |
No output schema declared.
No examples provided.
record_deployment_page_result Record Deployment Page ~468
Record one terminal page result for a deployment frame refresh. Every non-removed page in an initialized frame refresh must upload a newly staged desktop/mobile image pair from the exact active run, then submit those newly staged desktop/mobile version IDs and hashes with captureRunId and opaque captureProof. For unchanged, the server recomputes the image-byte hashes, accepts only an exact match to the frozen canonical pair, records the new evidence as observed, and discards the private duplicate pair; use updated if either byte hash differs. The deploy hook alone freezes removed rows, so callers cannot submit removed for an initialized run. Only server-confirmed historical pre-frame not_requested receipts retain a legacy no-run route. The server finalizes only after every initialized page has the current exact capture-run pair; a Critique queue state alone is never frame-current.
| Name | Type | Req | Description |
|---|---|---|---|
| captureProof | string | – | Opaque proof from start_deployment_capture_run. Required with captureRunId for every initialized terminal result; never persist, log, or pass it through shell argv. |
| captureRunId | string | – | Active capture-run ID from start_deployment_capture_run. Required for every initialized frame-refresh terminal result. An initialized removed result is forbidden because the deploy hook freezes remov… |
| contentHashes | array | – | Server-recomputed SHA-256 hashes of the exact newly uploaded image bytes, paired with versionIds. |
| deploymentId | string | yes | Deployment event ID supplied by get_pending_critiques. |
| error | string | – | Bounded truthful reason for failed, inaccessible, or skipped results. Never include credentials or raw page content. |
| outcome | string | – | Optional local classifier outcome. The local MCP maps changed to updated and unknown to failed when status is omitted. |
| pageUrl | string | yes | Exact inventoried page URL. Query variants remain distinct. |
| status | string | yes | Terminal result. Use updated for a persistent change; use failed rather than labeling uncertain evidence unchanged. |
| versionIds | array | – | Newly staged desktop/mobile version IDs for updated, added, or unchanged. Unchanged still requires fresh current-run byte uploads; the server deduplicates only after verifying both byte hashes match… |
No output schema declared.
No examples provided.
record_pin_verification Record Verification ~160
Record a caller-reported verification verdict using the compatible legacy workflow. This does not independently prove deployment, check execution, or client acceptance. For pilot projects, submit_verification_report records append-only observations and attach_verification_run obtains separately validated check evidence.
| Name | Type | Req | Description |
|---|---|---|---|
| annotationId | string | yes | The pin ID being verified |
| notes | string | – | Optional plain-text verification notes (up to 2KB) explaining the verdict. |
| status | string | yes | Caller-reported verdict only: "verified" reports success, "regressed" reports a problem, "inconclusive" reports uncertainty, and "pending" records an intended recheck. No value proves independent exe… |
| verifiedAt | string | – | Optional ISO timestamp. Defaults to now. |
No output schema declared.
No examples provided.
register_deployment_discovered_pages Register Deployment Pages ~103
Register the exact bounded URL inventory discovered in one local browser context before staging deployment captures. The backend returns accepted pending pages; upload snapshots and record terminal results only for that returned subset, never for a locally guessed URL.
| Name | Type | Req | Description |
|---|---|---|---|
| deploymentId | string | yes | Deployment event ID supplied by get_pending_critiques. |
| pageUrls | array | yes | Exact URLs discovered in the current same-origin browser context. Harmless URL normalization is applied; query variants remain distinct. |
No output schema declared.
No examples provided.
remove_collaboration_integration Remove Integration ~94
Remove a Slack, Microsoft Teams, or Discord webhook subscription from a Pincushion project.
| Name | Type | Req | Description |
|---|---|---|---|
| integrationId | string | – | Exact integration ID from list_collaboration_integrations. |
| name | string | – | Subscription name to remove with provider. Default: default. |
| projectId | string | yes | The Pincushion project ID. |
| provider | string | – | Provider to remove when integrationId is omitted. |
No output schema declared.
No examples provided.
remove_member Remove Member ~54
Remove a collaborator from a Pincushion project. Frees up the seat if they were an editor.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | Email of the person to remove | |
| projectId | string | yes | The project ID |
No output schema declared.
No examples provided.
resolve_annotation Resolve Pin ~100
Mark an annotation as resolved after addressing the feedback. Optionally add a resolution comment explaining what was changed.
| Name | Type | Req | Description |
|---|---|---|---|
| annotationId | string | yes | The annotation ID (e.g. "ann_abc123") |
| comment | string | – | Optional comment explaining the resolution (e.g. "Changed label to Recent Orders in wmlHomePage.html line 42") |
| resolvedBy | string | – | Name to attribute the resolution to (defaults to "AI Agent") |
No output schema declared.
No examples provided.
resolve_quickstart_demo Finish Quickstart Demo ~94
Finish the quickstart demo loop after editing the demo copy. Confirms the change, returns the bridge to real usage, and cleans up the throwaway .feedback/.quickstart/ files. Does NOT create or resolve any real pin.
| Name | Type | Req | Description |
|---|---|---|---|
| annotationId | string | yes | The demo pin id you addressed (e.g. ann_demo_cta). |
| fixDescription | string | yes | One line describing what you changed. |
No output schema declared.
No examples provided.
search_annotations Search Feedback ~34
Full-text search across all annotation comments, selectors, component names, and tags.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Search query string |
No output schema declared.
No examples provided.
set_agency_coordination_pilot Set Agency Pilot ~90
Pilot: owner-only switch for the private agency coordination increment. It is off by default. Enabling it does not change prices, seats, stakeholder access, public reports, or existing pin workflows.
| Name | Type | Req | Description |
|---|---|---|---|
| enabled | boolean | yes | True enables the pilot for this project; false disables all agency-side readers/writes. |
| projectId | string | yes | Exact Pincushion project ID. |
No output schema declared.
No examples provided.
set_agency_pin_labels Set Agency Pin Labels ~68
Pilot: replace the private agency-label set on one pin. Every label must belong to the same exact project and be active; cross-project and archived labels fail closed.
| Name | Type | Req | Description |
|---|---|---|---|
| annotationId | string | yes | – |
| labelIds | array | yes | – |
| projectId | string | yes | – |
No output schema declared.
No examples provided.
set_slack_preferences Slack Preferences ~529
Read or update the caller's Slack DM preferences. Resolves the user via license_key → email, then applies the change across every Slack workspace the email is linked to. Call with no args to see current state. Call with `mute: "1h"` (or "today", "forever", "off") to silence DMs for a window. Call with `eventNewPin: false` (or any event_* flag) to toggle individual event types off. Same surface as the App Home toggles and `/pincushion mute`, accessible from the agent — useful for "mute pin DMs during this refactor" workflows.
| Name | Type | Req | Description |
|---|---|---|---|
| digestMode | string | – | Delivery cadence. "instant" is the default; "hourly" and "daily" are reserved for a future digest implementation. |
| eventAgentPinCreated | boolean | – | DM when a QA/browser agent files a pin. Off by default. |
| eventCreditPackPurchased | boolean | – | DM when an AI-action credit pack is added to your license. Off by default (owner receipt). |
| eventEmailPinCreated | boolean | – | DM when feedback arrives via inbound email. Off by default. |
| eventFollowUp | boolean | – | DM on replies in threads you authored or commented on. |
| eventMention | boolean | – | DM on @-mentions of you. |
| eventNewPin | boolean | – | DM on new pins. |
| eventPinDeployed | boolean | – | DM when a fix deploys to production. Off by default. |
| eventPinImplemented | boolean | – | DM when a fix is committed (before it is live). Off by default. |
| eventPinReady | boolean | – | DM on pins marked ready for implementation. |
| eventPinVerified | boolean | – | DM when Pincushion AI verifies a fix shipped correctly (the loop-closer). On by default. |
| eventReportCreated | boolean | – | DM when a teammate shares a crit report. Off by default. |
| eventResolved | boolean | – | DM on resolved pins. |
| mute | string | – | Friendly mute alias. "off" unmutes. |
| mutedUntil | string|null | – | Alternative to `mute`: ISO timestamp until which DMs are silenced, or null to unmute. |
| quietHoursEnd | integer | – | Quiet-hours end hour (0-23) in `timezone`. |
| quietHoursStart | integer | – | Quiet-hours start hour (0-23) in `timezone`. |
| timezone | string | – | IANA timezone (e.g. America/Los_Angeles) for quiet hours. |
No output schema declared.
No examples provided.
start_deployment_capture_run Start Frame Refresh ~98
Starts one short-lived local frame-refresh run for an exact deployment and returns its opaque proof once. Keep the proof only in process and pass it to authenticated upload_page_snapshot/record_deployment_page_result/complete_deployment_capture_run calls; never put it in capture-snapshot, shell argv, a report, pin, status message, or file.
| Name | Type | Req | Description |
|---|---|---|---|
| deploymentId | string | yes | Deployment ID from get_pending_deployment_frame_refreshes. |
No output schema declared.
No examples provided.
start_quickstart_demo Start Quickstart Demo ~132
Start the 60-second Pincushion quickstart: returns one sample stakeholder feedback pin (element selector + thread + acceptance criteria) on a bundled demo page that is copied to .feedback/.quickstart/landing.html. Edit ONLY that copy to satisfy the pin, then call resolve_quickstart_demo. Nothing is written to the real project or synced to the cloud. Use this to show a new user the full read-pin -> fix-code -> resolve loop.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | Return all 3 demo pins instead of just 1. Default false (one pin, ~60s). |
No output schema declared.
No examples provided.
submit_verification_report Submit Reported Verification ~130
Pilot: append a project-scoped caller-reported verification observation. An idempotency key makes retries safe. Reported success is not independent check evidence or client acceptance.
| Name | Type | Req | Description |
|---|---|---|---|
| annotationId | string | yes | – |
| deploymentEventId | string | – | Optional immutable deployment receipt ID. Never infer this from a deploy URL. |
| idempotencyKey | string | yes | Stable unique key for this exact report; reuse only for an identical retry. |
| notes | string | – | Plain-text observations, not a proof of check execution. |
| projectId | string | yes | – |
| status | string | yes | – |
No output schema declared.
No examples provided.
update_critique_context Update Critique Context ~399
Lightweight write-only path for the layered critique-context system. Use this from /setup and /refresh-brand after the dev agent has gathered repo signals (README, theme tokens, sample copy, competitor URLs, recent resolved pins) and compiled them into a critique brief. Unlike `configure_project`, this does NOT create a deploy hook, sync members, or validate URLs — it just persists the compiled brief (+ signals + policy) and pushes to cloud. Identify the project by `projectId` or `name`. The compiled `critiqueContext` is what the AI critic actually reads at pin time; `critiqueSignals` + `critiquePolicy` are inputs retained for traceability and the next recompile.
| Name | Type | Req | Description |
|---|---|---|---|
| critiqueContext | string | – | The compiled critique brief (max 8192 chars). Markdown encouraged. This is what the AI critic loads at pin time. Pass null to clear and force a recompile on the next run. |
| critiquePolicy | string | – | User-editable policy override (max 4096 chars). Persists across recompiles so users keep hand-tuned rules. Pass null to clear. |
| critiqueSignals | object | – | Raw signals JSONB. Recommended shape: { framework: e.g. "next-app-router"|"astro"|"static-html", projectType: "marketing"|"app"|"mixed", pages: [{ url, source, slice, headings, ctas, components, body… |
| name | string | – | The project display name. Used to look up the project when projectId is not known. |
| projectId | string | – | The project ID to update. Mutually exclusive with `name`. |
No output schema declared.
No examples provided.
upload_page_snapshot Upload Page Snapshot ~677
Upload a full-page screenshot that turns the public share report into an annotated page: viewers see the real page with numbered pin markers at true positions and click-to-open thread bubbles. Capture the page yourself (kill animations, scroll to force lazy loads, full-page shot, JPEG/WebP ≤5MB), resolve each open pin's element.selector to document-pixel coordinates IN THAT CAPTURE, and pass them as pinPositions. Owner/editor only. One snapshot per (project, page) — re-upload replaces it. pageUrl must match the pins' page_url verbatim.
| Name | Type | Req | Description |
|---|---|---|---|
| captureContext | object | – | Metadata for this exact responsive-web capture. Use deviceClass (desktop/tablet/mobile), cssWidth, cssHeight, dpr, orientation, and optional coarse platform/browser. Never label a scaled desktop imag… |
| captureFingerprint | object | – | Optional bounded v1 local change evidence derived from semantic structure and decoded screenshot tiles. It never contains pixels or readable page text. |
| captureProof | string | – | Opaque short-lived capture proof. Required with captureRunId for an initialized deployment frame refresh; never persist, log, or pass it through shell argv. |
| captureRunId | string | – | Active capture-run ID from start_deployment_capture_run. Required with an initialized deployment frame refresh. |
| contentHash | string | – | Optional SHA-256 of the exact JPEG/WebP bytes. The local server verifies it before upload; the backend verifies it again. |
| contentType | string | – | Default image/jpeg. PNG is rejected for page snapshots (size). |
| deploymentEventId | string | – | Legacy/internal alias for deploymentId. |
| deploymentId | string | – | Optional deployment event ID. When supplied, upload-screenshot stages this immutable capture without moving the canonical report head. Initialized frame refreshes require captureRunId plus capturePro… |
| height | integer | yes | Pixel height of the uploaded image (1–60000). |
| hotspots | array | – | Optional hit-regions in THIS image's pixel space, one per real element you can identify (nav item, button, labeled region…). When present, the public report's click-to-pin resolves a zero-install vis… |
| imageB64 | string | – | Base64 image data, if imagePath is not available. |
| imagePath | string | – | Absolute path to the JPEG/WebP file on disk (preferred — read server-side, keeps base64 out of the transcript). |
| pageUrl | string | yes | Exact page_url the pins carry — copy verbatim from get_annotations. The snapshot is keyed by this string. |
| pinPositions | array | – | Document-pixel coordinates of each pin in THIS image, resolved from element.selector at capture time. Pins omitted here render in the notes list only. |
| privateCritique | boolean | – | Store this Crit capture privately without replacing public latest snapshots. |
| projectId | string | yes | The project ID |
| width | integer | yes | Pixel width of the uploaded image (1–4000). Pin coordinates must be in this same space. |
No output schema declared.
No examples provided.
How do I install the Pincushion MCP server?
Pincushion runs locally as an npm package, launched with npx -y pincushion-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 · pincushion-mcp
claude mcp add jcooley8-pincushion -- npx -y pincushion-mcp
What is the Pincushion MCP server?
Pincushion is an MCP server listed in the public MCP registry as io.github.jcooley8/pincushion. Stakeholders pin feedback on your live app; your AI agent reads the pins via MCP and fixes them. This page covers its npm package (pincushion-mcp).
Is the Pincushion MCP server safe to use?
Pincushion 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. 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 Pincushion MCP server expose?
Pincushion exposes 67 tools: get_annotations, search_annotations, get_feedback_summary, get_component_feedback, resolve_annotation, and 62 more. Their descriptions and schemas cost roughly 12,209 tokens of context every time the server is loaded.
Is the Pincushion MCP server still maintained?
Pincushion 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.