"Answer" matching MCP servers:

This MCP server enables AI agents to submit a single technical answer along with caller-supplied concepts, accepted synonyms, and numeric requirements for deterministic, rubric-based feedback.

Enables Codex and Claude Code agents to submit drafts for local rubric-based review through TypeSafe Jev, returning keep, rewrite, or uncertain decisions so agents can fix flagged issues and re-check once.

Enables a coding agent to answer "is this iOS release ready?" by running read-only App Store Connect checks: build processing, App Review state, a 13-point submission preflight, release-notes policy linting, and App Store Server Notification reconciliation. The lone write capability is a dry-run-first, seven-gate submission tool that always requires explicit confirmation.

Checks a repository's own guardrails and fails any that are present but have stopped refusing anything. Three read-only tools: installation status, per-step verification that issues a receipt, and a tail of the append-only ledger recording every question and answer.

Reads a small-business website like a customer would and shows where they get stuck. Every AI answer has to quote the page, and the server checks the quote before it counts.

Turns JUnit XML test reports from CI into queryable QA metrics, letting AI assistants answer plain-English questions about failures, flaky tests, regressions pinned to a commit, root-cause clusters, and performance drift. Also generates ready-to-share QA health reports and self-contained HTML dashboards without logging into separate tools.

Lets assistants send the same test prompts to as many as four text models across OpenRouter, Amazon Bedrock, Google Vertex AI and Microsoft Foundry, then automatically grade each answer with a judge model, rule checks and a policy gate. Returns scored leaderboards with letter grades, per-response strengths and weaknesses, latency, throughput and estimated cost, plus downloadable PDF and CSV reports.

Enables MCP clients to check whether AI answer engines such as ChatGPT, Claude and Perplexity can read and cite a given site, reporting robots.txt rules, edge-level bot blocks, llms.txt, structured data, JS-only content and other citation blockers with a score and fixes. It can also draft a starter llms.txt file from a site's homepage.

Enables deterministic IELTS answer checking, evidence-grounded explanations, error-cause classification, spaced repetition of mistakes, and progress reports, with data stored locally.

Enables AI agents to interactively drive 1C:Enterprise UI through the testing client, including opening forms, clicking buttons, filling fields, and capturing evidence.

Enables AI coding agents such as Cursor and Claude Code to browse KaDeep projects, suites, test cases, runs, jobs and defects, run end-to-end tests, and check localization quality directly as tools. It exposes 14 tools over stdio so agents can answer questions like which smoke tests fail and why, or trigger the checkout tests themselves.

Enables AI assistants to answer QA questions in a single call, covering run reports, failure grouping by root cause, flaky versus regressed test detection, and coverage gaps. Also exposes raw TestRail API access when a question needs it.

Enables coding agents to query a precise, local call/type/data graph so they can find who calls what, what breaks when code changes, and which tests to run, with every answer traced to file:line.

Evaluates RAG outputs on faithfulness, answer relevancy, and context precision using an LLM-as-a-Judge backend. Exposes tools for running evaluations, scoring individual samples, and checking thresholds, enabling CI gating and on-demand assessment via MCP.

Enables an agent to verify every number in its answer against the tool outputs of the same session, storing recorded outputs and flagging fabricated values that no tool produced. It exposes check, record, and reset tools so agents can recompute, correct, or drop unvouched numbers before finalizing.

Enables AI coding agents to publish work mid-task for a real human reviewer, who returns comments pinned to the exact elements that are off and a verdict, so the agent can iterate until a person approves. It also handles text-only questions where human judgment — design taste, wording, which version people prefer — is the answer.

Enables voice-first assistants to answer small-business compliance questions for Idaho and New Mexico LLCs, returning short spoken checklists, the next filing deadline, plain-language explanations of terms, and quick website accessibility checks. Every fee and rule is cited to a statute or official source, and unsupported states or unverified details are labeled unknown.

Enables auditing any website for AI-answer readiness, returning a score and actionable fix list based on llms.txt, schema, sitemap, and related checks.

Consolidates git history, test results, and Copilot sessions into a searchable SQLite database for AI assistants to answer questions about development activity.

Enables coding agents to drive iOS Simulators and Android emulators or devices by reading accessibility trees and delegating step selection to Jev, so agents only plan and answer occasional questions.