Squidler.io

MCPAI代理

提供方 squidlerio

AI代理 HTTP · 远程 API Key 社区 / 第三方 ClaudeCursorCodexZed
查看接入方式

Model Context Protocol (MCP) server that connects AI assistants like Claude to Squidler's accessibility and quality checking platform

一句话选型结论

按资料字段整理

Squidler.io 属于AI代理类 MCP 服务器,HTTP · 远程,API Key,可直接接入 Claude、Cursor、Codex 等,有可直接复制的远程端点配置。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类AI代理 传输方式HTTP · 远程 鉴权API Key 部署方式远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

AI代理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

testingdevelopmentweb app

安装与配置

HTTP · 远程 API Key
连远程 HTTPS 端点,通常为 Streamable HTTP
https://mcp.squidler.io

把它填进客户端的 MCP 配置即可,不需要在本地安装运行时。

  1. 1
    准备运行环境

    确认你的客户端支持远程端点,并拿到服务地址。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude、Cursor、Codex,换客户端不用重新研究配置。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 使用前要准备好API Key对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在AI代理场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Squidler.io当前 未标注 HTTP · 远程 远程部署 有 未标注
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方squidlerio上游标注的维护方 squidlerio
分类AI代理本站按上游分类展示
连接方式HTTP · 远程连远程 HTTPS 端点,通常为 Streamable HTTP
鉴权方式API Key远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · Cross-platform本地安装时用到的包标识与运行时
部署类型远程部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

14.2 KB
来自项目仓库与上游目录的原文,未做删改

Squidler MCP Server

Squidler.io

AI coding agents excel at the Build phase of a web app, but struggle with the Verify phase. Squidler is designed to validate your web app as a human based on natural language use cases, and without writing brittle, DOM-dependent tests.

Squidler is not just a testing tool; it enables your coding agent to analyze its own work from a user perspective, decoupled from the implementation. Squidler closes the autonomous Build → Verify → Fix loop, and enables you to act as the true human-in-the-loop who manages the outcome rather than the output.

Squidler MCP Server

With the Squidler MCP server you enable you AI coding agents, like Cursor, Claude Code, Replit, Lovable etc to work with Squidler. This means that you can have your coding agent build a feature, describe the use case in natural language for Squidler, ask Squidler to test it, to get the details of how the test run went, and details of all problems or friction that were found when using your web app.

Below are details and example for how to get started with Squidler via MCP. If you have any questions, don't hesitate to reach out to mattias@squidler.io.

Configuration

Add to your MCP client configuration:json { "mcpServers": { "squidler": { "transport": "http", "url": "https://mcp.squidler.io", "headers": { "Authorization": "Bearer YOUR_SQUIDLER_API_TOKEN" } } } }

Get your API token from squidler.io/integrations/api-keys.

Built-in Agent Guidance

The MCP server includes built-in instructions that teach your AI agent a Test-After-Feature Workflow. When connected, the agent automatically knows how to use Squidler without you having to explain it. The workflow it follows:

  1. Run existing tests — verify nothing is broken by the new feature.
  2. Investigate failures — use test run outcomes and events to understand what failed. Fix the code if it's a bug, or update/delete the test if it's obsolete.
  3. Label the feature — create a label for the completed feature (e.g., "User Login", "Checkout Flow") to organize your test catalog.
  4. Cover the new feature — create test cases for the new behavior using the guided conversation (test_case_create), tag them with the feature label, and run them to confirm they pass.
    - For pages with no clickable link (hidden endpoints, deep links), write steps as: "Navigate directly to /path"
  5. Confirm green — re-run until all tests pass, then move on to the next feature.

Over time this builds a growing catalog of tests organized by feature that prevents regressions and documents how the system is meant to work.

Resources

Resource URI Description
squidler://help Server documentation and available capabilities
squidler://sites List of all available sites

Tools

Sites

Tool Description
sites_list List all available sites
site_details Get site information (owner, URL, name, frontend link)
site_create Create a new site

Problems

Tool Description
problems_summary Overview of problems (total count by type)
problems_list List problems with pagination and filtering
problem_get Get detailed information about a specific problem
problem_resolve Mark a problem as resolved
problem_dismiss Mark a problem as false positive

Test Case Creation

Tool Description
test_case_create Start a guided conversation to create a high-quality test case stored on Squidler. Leverages site page knowledge, existing test coverage, and testing best practices. Returns a conversationId — continue with test_case_create_respond.
test_case_create_respond Continue an in-progress test-case-creation conversation — answer questions, review the draft, or confirm creation. Works for both test_case_create and test_case_create_standalone.

Test Cases

Tool Description
test_cases_list List all test cases
test_case_get Get test case details
test_cases_list_by_label List test cases with a specific label
validate_test_case Validate a test case for quality, feasibility, and best practices
test_case_update Update an existing test case (includes automatic validation feedback)
test_case_delete Delete a test case
test_case_run Run a single test case
test_cases_run_all Run all test cases
test_cases_run_by_label Run test cases with a specific label

Repo-Stored / Standalone Test Cases

For agents that manage test cases as markdown files in their own repo (no Squidler storage). Covers the create → validate → run → promote cycle. Particularly useful for local dev iteration: pair test_case_run_standalone with the @squidlerio/squidler-mcp npx proxy to route runs through a local Chrome against http://localhost:.

Tool Description
test_case_create_standalone Guided conversation that produces standalone markdown text (no Squidler storage). The architect asks more clarifying questions than the site-bound flow since it has no site context. Final result is {filename, markdown} for the agent to write to its local repo. Continue with test_case_create_respond.
validate_test_case_text Validate a System B test case file's markdown without running it. Returns typed errors for frontmatter, schema, and body problems, each with a file-line number when available. Use before writing generated files, after hand-edits, or in CI hooks.
test_case_run_standalone Run a test case supplied as inline markdown against a custom baseUrl (typically a localhost dev server or preview deploy). Step Optimization / Fixed Actions automatically draw on prior runs of the same (org, contentHash). Returns a checkId.
test_case_runs_standalone_list List past standalone runs for the caller's org with a given identifier, most-recent first. Standalone counterpart to test_runs_list — useful for dedup-before-rerun via content hash.
test_case_promote Promote a repo-stored markdown file into a site-bound test case on Squidler. Idempotent on (siteId, identifier): produces UNCHANGED, UPDATED, or CREATED depending on content-hash comparison with the latest revision.

Test Runs

Tool Description
test_runs_list List execution history for a test case
test_case_poll Long-poll for test execution status updates and events
test_run_outcome Get pass/fail outcome and goal results for a test run
test_run_events Get detailed execution events and screenshots
test_run_stop Stop a currently running test
pending_checks_list List checks queued (waiting to start) for a site, plus the currently running checks each is blocked by. Use when test_case_run returns queued: true.

Labels

Tool Description
labels_list List all labels
label_get Get label details
label_create Create a new label
label_update Update a label
label_delete Delete a label
test_case_labels_add Add labels to a test case
test_case_label_remove Remove a label from a test case

Headers

Tool Description
headers_list List custom headers for a site
header_add Add or update a custom header
header_delete Remove a custom header

Credentials

Tool Description
credentials_list List available login credentials
credentials_create_userpass Create credentials with explicit email/username and password
credentials_create_email Create credentials with auto-generated @squidlermail.io email for verification testing
credentials_create_oidc Create OIDC credentials for sites using OpenID Connect

Persona Reviews (UX Feedback)

Tool Description
personas_list List all available personas for UX reviews
persona_review_run Run a persona review on a validated test case
persona_review_findings Get detailed findings from a completed persona review
persona_findings_list List persona findings for a site and persona, filtered by status
persona_finding_triage Update finding status (RESOLVED, DISMISSED, IN_PROGRESS, OPEN)

Account Management

Tool Description
account_status Check current plan, remaining test quota, and available upgrades
account_upgrade_url Generate a short-lived URL to upgrade your plan

Prompts

Prompt Description
create-test-case Guided test case creation with goals, steps, and failure strategies
site-health-check Quick overview of site quality status with actionable recommendations
run-test-suite Run all or labeled tests and monitor results
get-started-with-squidler Complete onboarding: create site, generate initial tests, run them
suggest-initial-tests Analyze codebase to suggest 2-4 initial test cases
enhance-tests-from-runs Analyze test run events to identify and fix test weaknesses
identify-ux-improvements Discover usability issues from AI tester friction patterns
correlate-accessibility-and-ux Cross-reference accessibility problems with test execution friction
run-persona-review Run persona reviews on validated test cases to discover UX issues
migrate-legacy-tests Migrate legacy test cases to current format

Example Prompts

What you can say What it does
"Create a site for https://myapp.com called 'My App'" Register your website with Squidler to start monitoring and testing
"Analyze the codebase and create test cases for the key user flows" Uses guided conversations to create comprehensive test cases covering happy flows, edge cases, and negative tests
"Run all my test cases" Execute your test cases in a real browser with goal validation and issue detection
"Show me the results of my latest test runs" See which goals passed or failed, and understand what happened during execution
"Get the detailed test events for test case #1 and analyze the UX" Review execution logs to identify UX friction and usability issues
"Fix the issues preventing test case #1 from passing" Analyzes test failures and fixes the underlying code issues
"Get problem #42 and help me fix it" Address specific accessibility, functionality, or content issues
"Fix all accessibility issues in my site" Batch-fix WCAG compliance issues by iterating through problems

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Squidler.io 怎么安装?

在客户端按下面的安装命令接入:https://mcp.squidler.io。装完在客户端配置里引用同一个包或端点。

Squidler.io 怎么在 Claude、Cursor、Codex 里配置?

它的传输方式是HTTP · 远程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Squidler.io 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Squidler.io 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

Squidler.io 支持哪些客户端?

资料标注支持 Claude、Cursor、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Squidler.io 能提供哪些能力?

资料显示能力标签包括 testing、development、web app。具体工具清单以官方文档为准。

Squidler.io 需要什么运行环境?

运行时为 Cross-platform;属于远程端点,不需要在本地装运行时。

Squidler.io 是本地还是远程?

它是远程端点,连服务地址即可。传输方式为HTTP · 远程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。