Developer Tools
ia-qa.com
Provides utility functions for JSON formatting, UUID generation, hashing, token counting, and Base64 encoding, aiding in common development tasks.
ENDPOINT 1
https://www.ia-qa.com/mcp
MCP server metadata
- Name
- ia-qa-toolbox
- Version
- 1.0.0
IA-QA is a toolbox of QA/LLM testing primitives — each tool produces an actionable verdict (pass/fail, score, diff), and LLM tools are BYOK (the user supplies their own API key). To discover a tool without loading every schema, call find_tool with a keyword or category; call get_testing_guidelines for methodology. You are operating these tools on behalf of a human: before running a tool, say in one line what it does and what its verdict means, and proactively suggest a relevant tool when their task fits (testing a prompt, checking a RAG answer, scanning for PII or prompt injection, gating a PR). The same tools are also available from the shell via @ia-qa/cli, and local selector self-healing via @ia-qa/self-healing. Feedback wanted, not praise: after using a tool, call rate_tool when you have a real signal — low (1-2) if the output was wrong or a poor fit, high (4-5) only if it genuinely solved your need — and say in the comment what you were trying to do. Skip rating if you have nothing useful to report.
Known tools 150
count_tokensEstimate the token count of a text string using the cl100k_base approximation (~4 chars/token).
Inferred read-onlygenerate_slugConvert any string into a URL-friendly slug: lowercase, ASCII-normalized (é→e), special characters removed, spaces replaced with hyphens.
Inferred read-onlyvalidate_emailValidate an email address against RFC 5322 syntax before storing it, sending a transactional email, or adding it to a mailing list.
Potential side effectsminify_jsMinify a JavaScript snippet, function, class, or module up to 50 KB using Terser.
Inferred read-onlydecode_jwtDecode a JWT (JSON Web Token) and return its header and payload without verifying the signature.
Inferred read-onlytext_statsCompute comprehensive statistics for any text: character count (with and without spaces), word count, line count, sentence count, paragraph count, and estimated reading time in minutes.
Inferred read-onlygenerate_passwordGenerate a cryptographically secure random password using crypto.randomBytes.
Inferred read-onlyregex_testTest a regular expression pattern against an input string and return all matches with their index positions and named capture groups.
Inferred read-onlylorem_ipsumGenerate Lorem Ipsum placeholder text for UI mockups, design prototypes, or test data population.
Inferred read-onlytimestamp_convertConvert between Unix timestamps (seconds or milliseconds) and ISO-8601 / UTC date strings.
Inferred read-onlydiff_textCompute a unified line-by-line diff between two text strings (LCS algorithm).
Inferred read-onlytruncate_to_tokensTruncate text to at most N tokens (cl100k_base: ~4 chars/token) to avoid exceeding an LLM context window.
Inferred read-onlysplit_chunksSplit text into chunks of at most N tokens (cl100k_base: ~4 chars/token) with optional overlap.
Inferred read-onlyextract_json_from_textExtract the first valid JSON object or array embedded in chaotic LLM output (surrounded by markdown fences, prose, or explanatory text).
Inferred read-onlystrip_markdownStrip all Markdown formatting (headers, bold, italic, code fences, links, lists) from text and return clean plain text.
Inferred read-onlyescape_htmlEscape HTML special characters (&, <, >, ", ') to their safe HTML entities.
Inferred read-onlyunescape_htmlConvert HTML entities (&, <, >, ", ', and numeric &#NNN;) back to plain characters.
Inferred read-onlyfetch_veille_feedFetch the latest QA & AI/LLM articles aggregated from curated RSS sources (Google Testing Blog, DEV.to Testing/QA/AI/LLM/Agents, Hugging Face Blog, Simon Willison).
Inferred read-onlyscore_geo_signalsAnalyze a webpage <head> HTML (or full HTML) for GEO (Generative Engine Optimization) signals.
Inferred read-onlyextract_json_pathExtract a value from a JSON string using dot-notation path (e.g., "user.address.city", "items.0.name", "meta.tags").
Inferred read-onlygenerate_json_ldGenerate a ready-to-paste <script type="application/ld+json"> snippet for GEO / structured data optimization.
Inferred read-onlyanalyze_diff_bugsPattern-based diff linter: flags a fixed set of risky shapes in changed code — query-string interpolation (SQL/Cypher/Mongo injection shape), shell interpolation, eval/new Function, empty catch blocks, regex built from a variable, fewer catch blocks than before, and named authorization guards that disappeared.
Potential side effectsgenerate_test_casesGenerate a set of test cases (valid, edge, invalid) for a given feature description.
Inferred read-onlyvalidate_mcp_responseValidate that an MCP tool response conforms to expected format, schema, and content rules.
Inferred read-onlyllm_output_validatorValidate an LLM response against QA criteria: format checks (JSON, code, markdown), content rules (must-include, must-not-include), length constraints, language detection, and safety patterns.
Inferred read-onlyanalyze_responsesSemantically analyze N already-produced model outputs for the SAME task (the MCP counterpart to the LLM Sandbox).
Inferred read-onlyprompt_test_suiteDefine a test suite for a prompt: provide the system prompt, user prompt, and expected output criteria.
Inferred read-onlymcp_server_health_checkGenerate a health check report for an MCP server's tool manifest.
Inferred read-onlymcp_server_evaluateRun a full compliance evaluation against a live MCP server URL.
Inferred read-onlyjson_schema_validateValidate a JSON value against a JSON Schema (draft-07 subset).
Inferred read-onlyredact_piiAutomatically detect and redact Personally Identifiable Information (PII) from text.
Inferred read-onlytransform_json_arrayTransform a JSON array using common operations: pluck (extract specific fields), filter (by field value), sort_by (field), group_by (field), count_by (field), uniq_by (field).
Inferred read-onlycase_convertConvert a string between naming conventions: camelCase, PascalCase, snake_case, kebab-case, UPPER_SNAKE_CASE, dot.case, Title Case.
Inferred read-onlynumber_base_convertConvert numbers between bases: decimal, binary, octal, hexadecimal, or any base 2–36.
Inferred read-onlycron_validatorValidate a 5-field cron expression, explain the schedule, and preview the next execution times.
Inferred read-onlycalculate_readabilityCalculate readability scores: Flesch Reading Ease, Flesch-Kincaid Grade Level, Coleman-Liau Index, and Automated Readability Index.
Inferred read-onlynormalize_whitespaceNormalize whitespace: trim trailing spaces, collapse blank lines, normalize line endings (LF/CRLF), convert tabs to spaces.
Inferred read-onlyembedding_similarityCompute text similarity using local algorithms (Bag of Words, TF-IDF, Character N-grams).
Inferred read-onlyllm_format_checkValidate that an LLM output matches an expected format: JSON, Markdown, code block, bullet list, numbered list, table, YAML, XML, or custom regex.
Inferred read-onlyhallucination_checkWord-overlap based hallucination check: verifies if an LLM answer's words and numbers appear in the provided source/context.
Inferred read-onlyprompt_injection_scanScan user input or prompts for common prompt injection patterns.
Inferred read-onlytoken_budget_calculatorPlan token allocation across system prompt, user input, context/RAG chunks, and expected output.
Inferred read-onlyconsistency_checkCompare multiple LLM responses to the same prompt and detect inconsistencies using Jaccard word-overlap similarity and fact drift (number comparison).
Inferred read-onlyllm_json_schema_checkValidate that an LLM JSON output matches a JSON Schema definition.
Inferred read-onlylatency_benchmarkMeasure response time of one or more HTTP endpoints (GET/POST).
Potential side effectsresponse_quality_scoreScore an LLM response on multiple quality dimensions: relevance, completeness, clarity, conciseness, formatting.
Inferred read-onlyrag_relevance_rankRank an array of text chunks by relevance to a query using TF-IDF scoring.
Inferred read-onlytoxicity_scanScan text for toxic language, bias indicators, profanity, and harmful content categories.
Inferred read-onlyguardrail_testTest an LLM response against a set of guardrail rules: must-include, must-not-include, max length, required format, language, forbidden patterns, and custom regex.
Inferred read-onlyfunction_call_validateValidate an LLM function call / tool_use output: check that function name is in allowed list, arguments match expected schema, no extra/missing args.
Inferred read-onlyconversation_analyzeAnalyze a multi-turn conversation for context retention, topic drift, instruction following, and repetition.
Inferred read-onlymcp_schema_lintLint an MCP tool definition for best practices: naming conventions, description quality, schema completeness, required fields consistency, description length.
Inferred read-onlyab_test_reportGenerate an A/B test report comparing two prompts or model configurations.
Inferred read-onlycontext_window_checkGiven an array of message objects [{role, content}], estimate total token usage and check if it fits in the target model's context window.
Potential side effectsvector_similarityCompute similarity/distance between two float vectors: cosine similarity, dot product, Euclidean and Manhattan distance.
Inferred read-onlyvector_statsCompute statistics for a float vector or matrix of vectors: mean, std, L2 norm, min, max, sparsity, top-K indices.
Inferred read-onlybuild_rag_promptAssemble a complete RAG (Retrieval-Augmented Generation) prompt from retrieved context chunks and a user query.
Inferred read-onlysystem_prompt_builderBuild a structured system prompt from components: role, task, constraints, output format, tone, language, and examples.
Inferred read-onlymodel_infoGet detailed specs for an AI model: context window, pricing per 1K tokens, knowledge cutoff, provider, multimodal support, reasoning capabilities, and feature list.
Inferred read-onlycompare_modelsCompare 2-5 AI models side by side: context window, pricing, multimodal, reasoning capabilities, and provider.
Inferred read-onlyhttp_status_lookupLook up detailed information about any HTTP status code: class, name, description, cacheability, typical causes, and handling best practices.
Inferred read-onlyextract_todosExtract TODO, FIXME, HACK, BUG, NOTE, OPTIMIZE, and custom tags from any source code or text.
Inferred read-onlydetect_secretsScan code or config files for hardcoded secrets: AWS keys, GitHub tokens, OpenAI/Anthropic API keys, Stripe secrets, JWTs, database connection strings, and generic passwords.
Inferred read-onlycount_code_linesCount lines of code: total, code lines, comment lines, blank lines, and comment density.
Inferred read-onlylint_commit_messageValidate a git commit message against the Conventional Commits spec (feat, fix, docs, style, refactor, test, chore, ci, perf, build).
Potential side effectslevenshtein_distanceCompute the Levenshtein (edit) distance and normalized similarity ratio between two strings.
Potential side effectsformat_bytesConvert raw byte counts to human-readable sizes in SI (KB=1000) or IEC (KiB=1024) units, or parse size strings back to bytes.
Inferred read-onlydetect_languageDetect the natural language of a text using n-gram frequency analysis and common word markers.
Inferred read-onlylist_llm_modelsList all LLM models available on ia-qa.com with their provider, API endpoint, and capabilities.
Inferred read-onlyllm_generateGenerate text using open-source LLM models hosted on Groq (ultra-fast) or HuggingFace Inference (serverless).
Inferred read-onlyrerank_evaluateEvaluate RAG retrieval quality using the NVIDIA neural reranker (nv-rerankqa-mistral-4b-v3).
Inferred read-onlysecurity_headers_checkAnalyse the HTTP security headers of a public URL OR of raw response headers you paste in.
Inferred read-onlywebhook_endpoint_createCreate a temporary webhook endpoint that captures incoming HTTP requests for one hour.
Potential side effectswebhook_endpoint_requestsFetch the requests captured by a webhook created with webhook_endpoint_create.
Inferred read-onlyweb_security_auditRun a comprehensive web security audit combining headers, SSL, CORS, and cookies checks — then use an LLM to produce a prioritised remediation plan.
Inferred read-onlysecret_scanScan text or code for leaked secrets: API keys (AWS, GCP, Azure, OpenAI, Anthropic, Stripe, GitHub, GitLab, Slack, Twilio, SendGrid, HuggingFace), private keys (RSA/EC/PGP), JWTs, database connection strings, Bearer tokens, and Basic auth headers.
Potential side effectssimilarity_scoreCompute text similarity between reference and hypothesis using multiple metrics: Cosine (BoW, TF-IDF), Jaccard, ROUGE-1, ROUGE-2, ROUGE-L, and BLEU.
Inferred read-onlyneedle_haystack_generateGenerate a "needle in a haystack" test: embeds a target fact into a large block of filler text at a specified position.
Inferred read-onlyoptimize_prompt_tokensCompress an LLM prompt by removing filler words, verbose phrases, duplicate sentences, and unnecessary whitespace.
Inferred read-onlybias_detectAnalyse a set of LLM responses generated from the same prompt template but with different demographic variants (gender, origin, age, tone).
Inferred read-onlydiff_mappingsDiff a baseline page mapping against a current one and return a CI-style verdict: PASS / FIX / BLOCK, plus per-element drift (ok, renamed, healable, ambiguous, lost, added, rebound).
Inferred read-onlylist_local_testsDiscover .ia-eval.yaml LLM test suite files in the project directory.
Potential side effectsrun_eval_contractParse a .ia-eval.yaml LLM test suite, call the specified LLM model for each scenario, run all configured scorers, and return a structured JSON report with per-scenario Pass/Fail verdicts and a Markdown summary.
Potential side effectsgenerate_html_reportConvert a run_eval_contract() LLM Test Runner JSON result into a fully self-contained dark-themed HTML report with Pass/Fail badges, side-by-side Input/Output/Ground-Truth panels, evaluator score bars, and a radar chart.
Inferred read-onlyrun_vlm_test_suiteRun a test suite against a Vision-Language Model (VLM) — send an image (URL or base64) + N test cases (each with a question + assertion) to GPT-4o, Claude 3.5, or Gemini.
Potential side effectsmultimodal_eval_guideUnified tool for multimodal AI evaluation: set action=guide for reference thresholds/interpretation (CLIP, FID, VQA), or set action=clip_score / fid_score / vqa_accuracy / pipeline to compute real metrics via HuggingFace Inference API and VLM BYOK calls.
Inferred read-onlyrun_vlm_test_suite_batchCompare multiple VLMs on the same test suite in parallel — send an image (URL or base64) + N test cases to all models simultaneously.
Potential side effectsgenerate_eval_yamlGenerate a complete .ia-eval.yaml evaluation contract from a plain-language description of what your LLM should do.
Potential side effectsgenerate_ci_workflowGenerate a ready-to-commit GitHub Actions workflow that gates a build on IA-QA.
Inferred read-onlyvalidate_agent_trajectoryRun declarative assertions on an agent trace (OpenAI tool-call messages, LangChain run trees, or plain text logs).
Inferred read-onlyrun_semantic_testsSemantic assertion primitive: compare actual vs expected text pairs using cosine similarity + ROUGE-L.
Inferred read-onlytest_skillValidate a SKILL.md definition (Cursor / GitHub Copilot / Windsurf) by auto-generating trigger-positive and trigger-negative scenarios, running each through the model with the skill injected as a system prompt, and scoring trigger accuracy + step adherence.
Inferred read-onlyidentify_callerReturns what the server knows about the current MCP client: clientInfo captured during initialize, User-Agent, and any _meta fields sent with this request.
Inferred read-onlyopenapi_validateValidate the structure of an OpenAPI 3.x specification (JSON or YAML).
Inferred read-onlypost_jira_commentPost the output of jira_to_test_suite as a formatted comment on the source Jira ticket.
Potential side effectscreate_confluence_pageCreate a new Confluence page from the output of jira_to_test_suite.
Potential side effectsfetch_jira_issueFetch a complete Jira issue: summary, description converted to Markdown, status, assignee, priority, labels, custom fields, and optionally comments and attachment metadata.
Inferred read-onlyjira_to_test_suiteTransform a Jira ticket into a complete test suite: Gherkin scenarios, E2E steps, API test cases, test data matrix, and ambiguity detection.
Inferred read-onlyfetch_confluence_pageFetch a Confluence page and return its content as clean Markdown.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.ia-qa-toolbox]
url = "https://www.ia-qa.com/mcp"
enabled = trueClaude Code
.mcp.json
{
"mcpServers": {
"ia-qa-toolbox": {
"type": "http",
"url": "https://www.ia-qa.com/mcp"
}
}
}Claude Desktop
Settings → Connectors → Add custom connector
Name: ia-qa-toolbox
Remote MCP URL: https://www.ia-qa.com/mcpAdd this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"ia-qa-toolbox": {
"url": "https://www.ia-qa.com/mcp"
}
}
}Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"ia-qa-toolbox": {
"type": "http",
"url": "https://www.ia-qa.com/mcp"
}
}
}Generic MCP
Client-specific MCP configuration
{
"name": "ia-qa-toolbox",
"transport": "streamable-http",
"url": "https://www.ia-qa.com/mcp"
}MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for ia-qa.com was fetched 2026-08-16T22:14:38.725Z.
ia-qa.com is assessed as Trusted: Domain has an established technology history spanning over a year.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.