Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
คำอธิบายจากผู้ทำ (ภาษาอังกฤษตามต้นฉบับ)
30+ deterministic dev and delivery tools: linting, metrics, diagrams, model advice, AI-text checks.
สามเรื่องนี้ไม่รวมเป็นคะแนนเดียว เพราะความเห็น การวัด และความนิยม เป็นคนละเรื่องกัน
ตัวนี้ยังไม่ได้เรียบเรียงเป็นภาษาไทย ด้านล่างคือข้อเท็จจริงที่เราอ่านจาก registry
เลือกโปรแกรม AI ที่คุณใช้ แล้วคัดลอกค่าตั้งไปวาง
Authorizationค่าที่ติดป้ายความลับคือกุญแจของบัญชีคุณ อย่าส่งให้ใคร และอย่าวางในแชต
ต้องเตรียมก่อน
คุณใช้แอปไหน
เลือกแอปด้านบน เราจำไว้ให้ ครั้งหน้าปุ่มจะขึ้นว่า “ติดตั้งลง …”
ที่อยู่นี้ต้องใส่ key ใน header ของคำขอ ซึ่งเมนูเพิ่ม connector ใส่ให้ไม่ได้ ใช้ Claude Code, Cursor หรือ VS Code แทน
พิมพ์คำสั่งนี้ใน Terminal
claude mcp add --transport http api https://api.quasslabs.com/mcp --header 'Authorization: ใส่ค่าของคุณ'เติมค่าที่เว้นว่างไว้ก่อนรัน
วางในไฟล์ .cursor/mcp.json ของโปรเจกต์ หรือ ~/.cursor/mcp.json
{
"mcpServers": {
"api": {
"url": "https://api.quasslabs.com/mcp",
"headers": {
"Authorization": "ใส่ค่าของคุณ"
}
}
}
}เบราว์เซอร์จะถามก่อนเปิดแอป จากนั้นแอปแสดงค่าตั้งให้ตรวจแล้วกดยืนยัน ช่อง key เว้นว่างไว้ให้คุณใส่เอง
วางในไฟล์ .vscode/mcp.json ของโปรเจกต์
{
"servers": {
"api": {
"type": "http",
"url": "https://api.quasslabs.com/mcp",
"headers": {
"Authorization": "ใส่ค่าของคุณ"
}
}
}
}เบราว์เซอร์จะถามก่อนเปิดแอป จากนั้นแอปแสดงค่าตั้งให้ตรวจแล้วกดยืนยัน ช่อง key เว้นว่างไว้ให้คุณใส่เอง
ที่อยู่นี้ต้องใส่ key ใน header ของคำขอ ซึ่งเมนูเพิ่ม connector ใส่ให้ไม่ได้ ใช้ Claude Code, Cursor หรือ VS Code แทน
ตัวเลือกเก็บในคุกกี้บนเครื่องนี้ ไม่ต้องมีบัญชี
Authorization ความลับ HTTP headerค่าตั้งนี้สร้างจากข้อมูลใน registry ของผู้ทำ ถ้าไม่ตรงกับ README ให้เชื่อ README
ชื่อและคำอธิบายเครื่องมือตามที่ server ตอบมาเมื่อ 9 พ.ย. 2569 ผู้ทำเป็นคนเขียน ไม่ใช่เรา แสดงเป็นข้อความล้วน
alignment_gateRun an AI system prompt (and optional agent config) through a 45-criterion alignment/safety rubric. Returns a letter grade (A-F), numeric score, per-flag remediation, and a pass/fail verdict.
blm_land_lookupLook up Bureau of Land Management land status for a US coordinate: BLM ownership, jurisdiction, allowed activities (rockhounding, camping), permit requirements, and special designations (ACEC, Wilderness, WSA, NM/NCA).
diagram_contrastDiagram quality QA. Catch and fix the things that ruin diagrams: (1) unreadable label contrast - POST a mermaid/SVG or HTML diagram, get every WCAG-AA failure (incl. mermaid -block label colors, with unresolvable fills flagged honestly, not false-passed) + auto-corrected colors;
humanizer_scoreDetect AI-writing tells in text. POST prose and get a 0-1 ai_ness score + band (low/medium/high) + the EXACT patterns that fired (AI vocabulary, significance inflation, promotional language, filler phrases, negative parallelism, rule-of-three, em-dash overuse) with sample spans.
saas_metricsSaaS health advisor. POST your MRR/customers (+ optional churn/CAC/margin/growth) and get ARR/ARPA/LTV/CAC/payback/Rule-of-40/NRR/GRR computed, each with a health tag, plus an overall grade + a ranked "what to fix first" focus list. Deterministic math + advisory, no LLM.
acceptance_criteria_validatorQA advisor: validate acceptance criteria quality. POST a list of AC (or a story) and get per-AC problems (vague/untestable, non-atomic, no observable outcome) + a missing-coverage flag if there is no failure-path AC, plus a 0-100 score and pass/needs_work verdict. Tells you exact
coverage_checkScope-completeness advisor. POST a brief (or requirements[]) + your stories[] and get a coverage score + the gaps (requirements no story covers), orphan stories (possible scope creep), and missing structural buckets (auth/CRUD/error-states/tests). Tells you what the scope is miss
defect_triageBug-triage advisor. POST one bug report (or a list) and get severity (critical/high/medium/low), category, whether it has repro steps, and what info is missing (no repro / no expected-vs-actual / no environment). For a list: priority ranking + likely-duplicate clusters. Determini
model_advisorLLM selection + cost advisor. POST a task description (+ optional volume/tokens/constraints like local-only or cheap) and get a recommended model + fallback chain + do-not-use (with reasons), the complexity tier, and per-run + monthly cost. A maintained model+price catalog. Deter
tool_advisorWhich QL-API endpoint fits this task. POST a task description and get the ranked endpoint(s) that best match, each with a confidence label (high/medium/low). Deterministic keyword matching over this platform's own endpoint catalog, no LLM. Pairs with model_advisor (which itself i
humanize_textRewrite text to remove AI-writing tells. POST prose and get it back with the mechanical tells fixed (AI vocabulary swapped for plain words, filler phrases stripped, em-dash overuse reduced, significance inflation deflated) plus a change log, before/after ai-ness scores, and a res
dependency_checkCheck dependency manifests. Price: free by default; with live: true, 2 credits up to 50 packages, +1 per further 50, max 5 (200 packages). Default: offline hygiene lint for unpinned, wildcard or unbounded versions, missing lockfiles, git/URL deps, non-https indexes, install scrip
log_audit_creatorGenerate a concrete audit-logging spec for an app. POST your feature list (and optional compliance targets: soc2/hipaa/gdpr/pci) and get a full audit-event catalog (namespaced event names, actor/target/required fields, PII flags, retention), a canonical event envelope schema, a s
log_analyzerAnalyze a log file. POST raw log text (or an upload_id from the create_upload tool, up to 5MB) and get: level breakdown + time range, error clusters (messages normalized so variable ids/numbers collapse into one signature, with counts + first/last seen + a sample), a timeline, de
ticket_lintFull Jira-ticket quality linter (whole ticket, not just AC - use acceptance_criteria_validator for the deep AC pass). POST one ticket or a batch (max 50) and get per-ticket findings with severity + concrete fixes: missing/weak summary or description, missing AC or estimate, bugs
story_lintDeterministic structural quality linter for user stories - a sibling to ticket_lint but scoped to story-writing concepts any team recognizes: narrative completeness (As-a/I-want-to/So-that/Summary), acceptance criteria presence, duplicate/unknown dependency IDs, a "Manage X" stor
estimate_sanityDeterministic classifier for story/task hour estimates against benchmarks: flags each estimate in_range, borderline, over, under, or unbenchmarked. Supply either an explicit {min, max} range per type (benchmarks) or a list of historical actual hours per type (historical) that thi
pr_description_lintDeterministic PR description quality linter: flags a missing/too-short body, absent test evidence, absent stated rationale, an unstructured long body, and - only for PRs that look like bugfixes (title prefix fix/bug/hotfix/patch, or an explicit is_bugfix flag) - missing repro ste
commit_hygieneDeterministic commit-message hygiene checker: conventional-commit format, vague-subject detection, subject-length limit, a same-message secret-pattern scan (AWS keys, private key headers, Slack/GitHub tokens, inline password=/secret= style credentials - checked against the messag
readability_gradeDeterministic Flesch Reading Ease and Flesch-Kincaid Grade Level for a block of text, plus word/sentence/syllable counts and a plain-language reading-ease band (very_easy through very_confusing). Syllable counting is the standard vowel-group heuristic (same approximation used by
regex_lintStatic safety analysis of a regular expression plus an English explanation of what it matches. Parses the pattern into an AST and flags the structures that cause catastrophic backtracking (ReDoS): nested unbounded quantifiers like (a+)+, repeated alternations whose branches can s
mcp_tool_lint ดูเหมือนสั่ง AIStatic review of MCP tool definitions, as returned by a server's tools/list, for how well a model can choose and call them. Flags missing, too-short or vague descriptions; parameters with no description or type; free-form objects and arrays without items; required fields that are
openapi_diffCompares a base and a head OpenAPI 3.x spec (JSON object, or a JSON or YAML string) from the API consumer's point of view and lists what would break existing clients: removed operations or 2xx responses, new required parameters or request properties, optional-to-required changes,
actions_auditStatic security audit of GitHub Actions workflow files. Flags template injection (attacker-controlled github.* contexts such as a PR title or branch name expanded inside run: or actions/github-script), pull_request_target and workflow_run triggers and the pwn-request pattern of c
agent_card_lintStatic lint of an A2A (Agent2Agent) Agent Card, the JSON an agent publishes at /.well-known/agent-card.json. Checks conformance with A2A v1.0.1 and the 0.3 field names (both dialects accepted): required fields present and typed, URLs absolute https (http allowed for localhost), i
data_transformFive deterministic data utilities behind one tool, chosen by operation. csv_normalize: sniffs the delimiter, strips the BOM and normalises line endings, snake_cases headers (duplicates renamed), pads or trims ragged rows, drops empty rows and optionally duplicate rows, and return
skill_lint ดูเหมือนสั่ง AIStatic lint of an agent instruction file: an Agent Skills SKILL.md (YAML frontmatter plus markdown body) or an AGENTS.md / CLAUDE.md style file. For skills, checks the frontmatter against the Agent Skills specification: name present, lowercase-hyphenated, at most 64 characters an
sql_migration_lintStatic lint of a SQL migration file (Postgres or MySQL) for operations that lock or rewrite live tables or break running application code. Flags CREATE INDEX without CONCURRENTLY and concurrent index builds inside a transaction, foreign key, CHECK and UNIQUE constraints added wit
sprint_healthSprint/delivery health advisor. POST 1-24 sprints (committed/completed points, optional per-ticket estimate-vs-actual data) and get computed metrics each with a good/warn/bad health tag: velocity avg + trend + stability, commitment reliability, spillover rate, mid-sprint scope ch
worklog_guardrailWorklog/timesheet policy checker - run a batch of worklog entries through configurable guardrails BEFORE posting them to a time-tracking system. Checks: rounding increment (default 0.25h, float-safe), per-entry min/max, per-author daily totals, duplicates, over-estimate alerts (n
create_uploadGet a presigned S3 PUT URL to upload a file (policy doc, config, log, up to 5MB) that a file-ingesting endpoint then reads by upload_id. Two-step: call this, PUT your file to the returned url, then pass upload_id to the consuming endpoint. Uploads auto-expire in 1 day and are rea
send_feedbackSubmit free-text feedback about the API - a bug, an idea, a docs gap, a billing question, or anything else. Missing a tool? Use kind tool_request to tell us what you needed, with an optional tool_description. Tied to your key so we can follow up, but not a support-ticket SLA. Aut
accountEverything about your QuassLabs API account, chosen by `action`. Free: no action costs credits. "signup" (no API key needed): request a free key for an email address. A confirmation link is emailed; a human opens it on quasslabs.com to see the key, which is never returned to the
rate_callRate a specific prior metered call - thumbs up or down, plus an optional comment - keyed by the request_id that call's response reported. Works for any metered tool, so you can tell us when a result was wrong, unhelpful, or missed something. Resubmitting the same request_id overw
supply_chain_scanScan a whole repo archive (a ZIP of manifests, lockfiles and MCP server configs) for packages, MCP servers and extensions listed in a known-compromise catalog (Bumblebee threat intel). Use this for a repo, many lockfiles or MCP configs; use dependency_check instead to lint a few
describe_diagramTurn a plain-English description into Mermaid diagram source. Describe the flow, system, schema or timeline you want ("a login flow with an OAuth branch and a failure path") and get back complete, valid Mermaid - no need to know the syntax. The mermaid field of the response is di
convert_diagramMake Mermaid diagrams portable. Takes HTML containing blocks (or a raw Mermaid source) and returns the same document with every diagram pre-rendered to inline SVG and the Mermaid CDN runtime stripped. A CDN-backed diagram only renders if the reader can fetch and run the runtime;
เราตรวจจากข้อมูลที่ใครก็เปิดดูได้ ยังไม่ได้อ่านโค้ด ข้อที่ไม่เกี่ยวกับตัวนี้ไม่นับในตัวหาร · ตรวจเมื่อ 9 พ.ย. 2569
ชื่อใน registry ยืนยันโดเมน quasslabs.com แล้ว (registry ตรวจความเป็นเจ้าของโดเมน)
ยังไม่ได้อ่านข้อมูล repo จาก GitHub
ยังไม่ได้อ่านข้อมูล repo จาก GitHub
ตอบกลับใน 642 ms (HTTP 200)
ไม่ต้องล็อกอิน
คำอธิบายเครื่องมือ 2 ตัวมีข้อความที่ดูเหมือนสั่ง AI อ่านรายการด้านล่างก่อนติดตั้ง
เทียบกับทุก server ที่ยังใช้งานในหมวดนี้ทั้งทะเบียน ดาวนับเฉพาะเมื่อผู้ลงทะเบียนเป็นเจ้าของ repo
จากการตรวจเบื้องต้นของเรา ผ่าน 2 จาก 3 ข้อที่ตรวจได้ เรายังไม่ได้อ่านโค้ด ก่อนใส่กุญแจหรือ token ให้ดูว่า server ขอสิทธิ์อะไร และเลือกกุญแจที่ทำได้เท่าที่จำเป็น
ต้องใส่ค่าเหล่านี้: Authorization
รันบนคลาวด์ของผู้ทำ ต่อผ่านอินเทอร์เน็ตได้เลย ไม่ต้องลงโปรแกรม แต่ข้อมูลที่ส่งให้จะผ่านเซิร์ฟเวอร์ของผู้ทำ
repo บน GitHub มีการแก้โค้ดล่าสุด – และส่งรุ่นล่าสุด (0.4.0) เข้า registry วันนี้
โปรแกรมที่รองรับ MCP เช่น Claude Desktop, Claude Code, Cursor และ VS Code ตัวนี้ต่อผ่าน URL จึงใช้กับโปรแกรมที่รับ remote MCP ได้ เช่น ChatGPT ที่เปิดโหมดนักพัฒนา
ในหมวดเดียวกันมี Figma Context MCP, Claude Real Video, Figma MCP Server
server หมวดเดียวกันจากผู้ทำคนอื่น เรียงตามดาว
อ่านการ์ด:↓ ดาวน์โหลดต่อสัปดาห์i★ ดาว GitHubiสามเสา: รีวิว · ผลตรวจ · การใช้งานiอัปเดต = วันที่ส่งรุ่นล่าสุดเข้า registryi
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
server ทางการของ Figma ส่งข้อมูลงานออกแบบให้ AI อ่าน เพื่อเปลี่ยนแบบเป็นโค้ดหรืออธิบายแบบได้ตรงขึ้น ต่อผ่านคลาวด์ของ Figma
ส่วนนี้คัดจาก repo ของผู้ทำตามต้นฉบับ PopNx MCP ไม่ได้ตรวจหรือรับรองเนื้อหา ตัด HTML รูปภาพ และสคริปต์ออกแล้ว ลิงก์จะพาออกนอกเว็บ
32 deterministic developer and delivery tools over one authenticated MCP endpoint. No LLM in the loop for most of them: they are scorers, linters, validators and calculators, so results are reproducible and cheap. Covers prompt-safety grading, AI-writing detection and rewriting, LLM selection and cost advice, ticket/story/PR/commit linting, sprint and SaaS metrics, log analysis, dependency hygiene and supply-chain scanning, MCP tool linting, Mermaid diagram generation and offline rendering, and BLM land lookup.
Endpoint: https://api.quasslabs.com/mcp · Transport: streamable HTTP (stateless JSON-RPC 2.0) · Server version: 0.2.0
Documentation: https://docs.quasslabs.com
Every client sends the same thing: a Bearer qlk_... API key in the Authorization header. Hosts that reserve Authorization for themselves can send X-API-Key: qlk_... instead.
Claude Code
claude mcp add --transport http quasslabs https://api.quasslabs.com/mcp \
--header "Authorization: Bearer qlk_YOUR_KEY"
Cursor (~/.cursor/mcp.json, or .cursor/mcp.json in a project)
{
"mcpServers": { "quasslabs": { "url": "https://api.quasslabs.com/mcp", "headers": { "Authorization": "Bearer qlk_YOUR_KEY" } } } }
Any other client that supports streamable HTTP
{
"mcpServers": { "quasslabs": { "type": "http", "url": "https://api.quasslabs.com/mcp", "headers": { "Authorization": "Bearer qlk_YOUR_KEY" } } } }
Or call it directly:
curl -sS -X POST https://api.quasslabs.com/mcp \
-H 'Content-Type: application/json' \ -H 'Authorization: Bearer qlk_YOUR_KEY' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"account","arguments":{"action":"balance"}}}'
Getting a key. Sign up at https://quasslabs.com/api, or from inside an agent with the account tool (action: "signup", no key needed). Either way you get an email with a one-time link, and the key is shown on quasslabs.com, never in the agent transcript. Every key gets 300 free credits each month.
initialize, tools/list and ping are unauthenticated, so any client or registry can discover the catalogue without credentials. tools/call requires the API key, except the account tool's signup and checkout_status actions. Keys are stored only as a SHA-256 hash, so a lost key cannot be recovered, only revoked and reissued.
Prepaid credits, 1 credit = $0.01:
| Pack | Price | Credits |
|---|---|---|
| Starter | $5 | 500 |
| Pro | $20 | 2,500 |
Buy a pack from inside an agent with the account tool (action: "buy_credits" returns a Stripe Checkout link for a human to pay), and check what is left with action: "balance". Each key's free monthly credits are spent before purchased credits and refill on the first day of each UTC month.
Failed calls are not billed: a call rejected before the tool runs (bad input, missing key, rate limit, insufficient credits) costs nothing, and a call that fails on our side (any 5xx) is refunded automatically. That includes supply_chain_scan archives that download but are rejected (not a ZIP, an unsafe path, too many entries, or too large once extracted): the archive is checked before anything is charged. A convert_diagram call whose diagrams all fail to render (422 mermaid_render_failed) or whose output is over the size limit (413 output_too_large) is refunded too.
Credits are per successful call. Tools marked 0 are free but still need a key.
| Tool | Credits | What it does |
|---|---|---|
alignment_gate | 35 | Grade an AI system prompt against a 45-criterion alignment/safety rubric: letter grade, per-flag remediation, pass/fail |
humanizer_score | 0 | 0-1 AI-ness score plus the exact patterns that fired |
humanize_text | 1 | Rewrite prose to strip mechanical AI-writing tells |
readability_grade | 0 | Flesch Reading Ease and Flesch-Kincaid Grade Level with a plain-language band |
| Tool | Credits | What it does |
|---|---|---|
model_advisor | 0 | Recommended model, fallback chain, do-not-use list, and a cost comparison for a task |
tool_advisor | 0 | Which of these tools fits a task, ranked with a confidence label and the MCP tool name to call |
dependency_check | 0 | Lint pasted dependency manifests for hygiene: pinning, lockfiles, insecure sources, install scripts, dependency confusion |
supply_chain_scan | 5 | Scan a whole repo ZIP (manifests, lockfiles, MCP server configs) against a known-compromise catalog |
log_analyzer | 5 | Level breakdown, time range, and normalized error clusters from a raw log file (up to 5MB) |
log_audit_creator | 5 | Feature list in, concrete audit-event catalog out, optionally targeted at SOC2/HIPAA/GDPR/PCI |
regex_lint | 1 | ReDoS risk analysis plus a plain-English explanation of a regular expression; compiles the pattern but never runs it |
mcp_tool_lint | 1 | Lint MCP tool definitions for model usability: vague descriptions, untyped parameters, near-duplicates, missing annotations, tool-poisoning phrases |
openapi_diff | 1 | Breaking-change report between two OpenAPI 3.x specs (JSON or YAML), with the semver bump it needs |
| Tool | Credits | What it does |
|---|---|---|
ticket_lint | 1 | Whole-ticket quality linter with severity-coded findings, batched up to 50 |
story_lint | 1 | User-story structure: narrative completeness, atomicity, testability |
acceptance_criteria_validator | 1 | Per-AC problems: vague/untestable, non-atomic, no observable outcome, missing coverage |
coverage_check | 1 | Requirements-vs-stories coverage score, gaps, and orphan stories (scope creep) |
defect_triage | 1 | Bug severity, category, repro-step presence, and what information is missing |
sprint_health | 1 | 1-24 sprints in, health-tagged delivery metrics out |
worklog_guardrail | 1 | Run timesheet entries through configurable policy guardrails before posting them |
estimate_sanity | 1 | Classify story/task hour estimates against benchmarks: in-range, borderline, over, under |
pr_description_lint | 1 | Missing body, absent test evidence, absent rationale, unstructured long body |
commit_hygiene | 1 | Conventional-commit format, vague subjects, length limits, and a secret-pattern scan |
| Tool | Credits | What it does |
|---|---|---|
describe_diagram | 5 | Plain-English description in, Mermaid diagram source out |
convert_diagram | 1 | Pre-render Mermaid to inline SVG so HTML works offline, in email, and in PDF exports |
diagram_contrast | 0 | Diagram QA: every WCAG-AA label-contrast failure in a Mermaid/SVG/HTML diagram, with fixes |
| Tool | Credits | What it does |
|---|---|---|
saas_metrics | 0 | ARR/ARPA/LTV/CAC/payback/Rule-of-40/NRR/GRR computed and health-tagged, plus an overall grade |
blm_land_lookup | 8 | BLM land status for a US coordinate: ownership, allowed activities, permit requirements, special designations |
| Tool | Credits | What it does |
|---|---|---|
account | 0 | One tool for your account. action: signup (email a one-time key link, no key needed), balance (credits, free credits left, reset date), buy_credits (Stripe Checkout link: $5 / 500 or $20 / 2,500), checkout_status (did a purchase land) |
create_upload | 0 | Presigned S3 PUT URL so file-ingesting tools can read a document by upload_id |
send_feedback | 0 | Submit a bug, idea, or docs gap against your key. Missing a tool? Send kind: "tool_request" |
rate_call | 0 | Thumbs up/down a prior metered call by its request_id |
tools/list only ever advertises what is callable right now. compress (LLMLingua-2 prompt compression, 10 credits) is built but temporarily switched off, so it is not listed.
humanize is now humanize_text, uploads is now create_upload, and feedback is now send_feedback. The REST endpoints (/v1/humanize, /v1/uploads, /v1/feedback) did not change.
This repository is the public manifest for the QuassLabs API MCP server: the registry entry, the tool catalogue, and connection instructions. The server is a hosted remote endpoint, so there is nothing to install and no server source here. The platform implementation is a commercial product and is not open source.
Report a problem with the MCP server through the send_feedback tool (free), or see SECURITY.md for security reports.