{"schema_version":"1.0","name":"ia-qa-toolbox-security","title":"IA-QA — 152 QA & Dev Tools for AI Agents","description":"The open QA workbench for LLM stacks. 152 testing primitives callable from Cursor, Claude Desktop, Windsurf, and any MCP agent. Prompt injection scan, hallucination check, semantic eval, RAG testing, VLM test suites, agent trajectory validation, guardrails, and classic dev tools (JSON, JWT, YAML, OpenAPI, encoding). No API key. No signup. Free.","homepage":"https://www.ia-qa.com","contact":"https://www.ia-qa.com/contactUs","attribution":"Powered by IA-QA (https://www.ia-qa.com) — free tools for developers & AI agents, by Jean-Christophe Jamet.","call_endpoint":"https://www.ia-qa.com/mcp/call","jsonrpc_endpoint":"https://www.ia-qa.com/mcp/security","pack":"security","pack_note":"This pack lists 30 of 152 tools. For the others, add https://www.ia-qa.com/mcp or another pack: most clients only call tools their server lists.","packs":{"security":{"jsonrpc_endpoint":"https://www.ia-qa.com/mcp/security","tools":30},"eval":{"jsonrpc_endpoint":"https://www.ia-qa.com/mcp/eval","tools":38},"data":{"jsonrpc_endpoint":"https://www.ia-qa.com/mcp/data","tools":36}},"discovery_hint":"This is a slim manifest. Use find_tool to search tools, GET /mcp/tool/{name} for full schema, or add ?full=1 to this URL for the complete manifest.","categories":["data","encoding","text","llm","qa","rag","dev","security","web","meta","eval"],"ecosystem":{"cli":{"name":"@ia-qa/cli","description":"Zero-dependency CLI — same 150+ tools from your shell. No signup, no API key. To know which tools to use to test an LLM, RAG pipeline or agent, call get_testing_guidelines without a topic.","install":"npm install -g @ia-qa/cli","usage":"ia-qa <tool> [input] [--flags]"},"self_healing":{"name":"@ia-qa/self-healing","description":"Local MCP server for UI test self-healing. Maps your app pages to role/name/selector contracts, diffs selector drift (PASS/FIX/BLOCK), and applies deterministic fixes to Cypress/Playwright/Selenium tests. Runs on your machine — nothing leaves it.","install":"npm install -g @ia-qa/self-healing","mcp_server":"ia-qa-heal-mcp","tools":["map_app","diff_mappings","fix_tests"],"requires":"Playwright (npx playwright install chromium)","cli_commands":["ia-qa-heal init","ia-qa-heal map","ia-qa-heal baseline","ia-qa-heal diff","ia-qa-heal fix"]}},"tools":[{"name":"find_tool","category":"meta","description":"Search available MCP tools by keyword or category before calling them. Returns matching tool names, descriptions, and optionally their inputSchemas. Call this when you are unsure which tool to use or want to explore the catalogue. Categories: data, encoding, text, llm, qa, rag, dev, security, web.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/find_tool","outputSchema":{"type":"object","properties":{"tool":{},"score":{},"query":{},"category":{},"count":{"type":"number"},"total_matches":{"type":"number"},"truncated":{"type":"boolean"},"tools":{"type":"array"},"hint":{}},"additionalProperties":true}},{"name":"prompt_injection_scan","category":"qa","description":"Scan user input or prompts for common prompt injection patterns. Detects system prompt overrides, jailbreak attempts, role manipulation, encoding tricks, delimiter attacks (chat-template tags `<|im_start|>`/`[INST]`/`<<SYS>>` AND fake role headers imitating markdown or chat separators: \"### System:\", \"--- SYSTEM ---\", \"---BEGIN SYSTEM OVERRIDE---\", \"---\nSYSTEM:\"), template/interpolation injection ({{...}}, ${...}), and context-exfiltration attempts (\"repeat everything above\"). A match inside quoted or fenced text (documentation citing a payload) is reported one severity level lower and marked `quoted` — never suppressed, since an LLM reading the document as data can still follow a quoted instruction. A quote preceded by a live imperative (\"output the following: ...\") keeps its full severity.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/prompt_injection_scan","outputSchema":{"type":"object","properties":{"risk_level":{},"injection_detected":{"type":"boolean"},"detections_count":{"type":"number"},"detections":{},"input_length":{"type":"number"},"sensitivity":{},"quoted_detections":{"type":"number"},"notes":{}},"additionalProperties":true},"guidance":{"gate":"signal-only","prefer":"a dedicated calibrated guardrail model for a hard gate"}},{"name":"guardrail_test","category":"qa","description":"Test an LLM response against a set of guardrail rules: must-include, must-not-include, max length, required format, language, forbidden patterns, and custom regex. Returns pass/fail per rule.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/guardrail_test","outputSchema":{"type":"object","properties":{"rule":{},"value":{},"label":{},"pass":{"type":"boolean"},"detail":{"type":"string"},"total_rules":{"type":"number"},"passed":{},"failed":{},"all_passed":{"type":"boolean"},"results":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"redact_pii","category":"security","description":"Automatically detect and redact Personally Identifiable Information (PII) from text. Replaces emails, phone numbers, SSNs, credit cards, IP addresses, and JWT tokens with [REDACTED_TYPE] placeholders. Safe to use before logging or sending to an LLM.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/redact_pii","outputSchema":{"type":"object","properties":{"redacted_text":{},"clean":{"type":"boolean"},"pii_found":{},"replacements":{},"total_redactions":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"secret_scan","category":"security","description":"Scan 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. Returns a list of findings with type, severity, line number, and a redacted preview. Use before committing code, sharing logs, or sending text to an LLM. 100% regex-based, zero network calls.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/secret_scan","outputSchema":{"type":"object","properties":{"risk_level":{},"secrets_found":{},"findings_count":{"type":"number"},"findings":{},"input_lines":{"type":"number"},"scanned_types":{},"summary":{"type":"string"}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"validate_agent_trajectory","category":"eval","description":"Run declarative assertions on an agent trace (OpenAI tool-call messages, Anthropic tool_use/tool_result blocks, LangChain run trees, or plain text ReAct logs). No LLM call — deterministic. Assertion types: order (tool A before B), must_call, must_not_call, max_calls, min_calls, no_error, recovery (agent completes a successful step after its last error). A step counts as errored when the trace says so — is_error/isError, status/state in {error,failed,exception,…}, an error field, a JSON body with error/success:false — or when its text payload STARTS with an error marker (Error:, Traceback, TypeError:). Model prose is never scanned for keywords, and every errored step reports error_signal naming what flagged it. Returns per-assertion PASS/FAIL, parsed steps, warnings (a trace parsing to 0 steps is flagged — assertions passing on emptiness prove nothing), and an overall verdict. Use this to gate CI/CD on agent behavior correctness.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/validate_agent_trajectory","outputSchema":{"type":"object","properties":{"verdict":{"type":"string"},"summary":{"type":"object","additionalProperties":true},"warnings":{"type":"array","items":{"type":"string"}},"results":{"type":"array","items":{"type":"object"}},"steps":{"type":"array","items":{"type":"object"}}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"validate_mcp_response","category":"qa","description":"Validate that an MCP tool response conforms to expected format, schema, and content rules. Use this to QA-test any MCP server tool. Supply the tool's actual JSON result and a set of checks to perform.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/validate_mcp_response","outputSchema":{"type":"object","properties":{"passed":{"type":"number"},"failed":{"type":"number"},"total":{"type":"number"},"checks":{},"verdict":{"type":"string"}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"mcp_server_health_check","category":"qa","description":"Check an MCP server's tool definitions without contacting it — for a server not deployed yet, a stdio server, or a CI gate. Paste the answer to tools/list (raw JSON-RPC or its result), a bare array of tools, one tool definition, or a manifest carrying name/description; input_shape says which one was read. Validates every tool against the MCP spec (name 1-128 chars of A-Z a-z 0-9 _ - .; camelCase and a tool with no parameters are valid; inputSchema of type object; required fields listed in properties) and, with strict, documentation (description ≥ 20 chars, every parameter with a description and a type). verdict: FAIL when a tool breaks a rule or no tool is found, WARN when only a manifest's server name/description is missing, PASS otherwise. A tools/list carries no server name, so those two checks are not scored on it (the name comes from initialize). Gate on verdict or on checks[tool_quality].pass.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/mcp_server_health_check","outputSchema":{"type":"object","properties":{"passed":{"type":"number"},"failed":{"type":"number"},"total":{"type":"number"},"verdict":{"type":"string"},"input_shape":{"type":"string"},"checks":{"type":"array"},"toolIssues":{},"stats":{"type":"object"}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"mcp_server_evaluate","category":"qa","description":"Run a compliance evaluation against a live MCP server over Streamable HTTP, the way a client meets it. Checks: initialize (protocol version, serverInfo, Mcp-Session-Id carried afterwards), notifications/initialized (202), tools/list with pagination, the spec's tool-definition rules, ping, an unknown method (-32601), one tools/call, GET on the endpoint (SSE or 405), and P50/P95 latency over pings. JSON and SSE answers are both read. Only a tool you name in test_tool_name, or one the server annotates readOnlyHint: true, is called — otherwise the call is skipped and not scored. Returns PASS/FIX/BLOCK with a 0-100 score and per-check details; INCONCLUSIVE (score null) when the server requires authorization, since no credentials are sent. A 301/302 on POST caps the verdict at FIX. The call runs from ia-qa.com: private and local addresses are refused, and stdio servers cannot be reached — for those, paste their tools/list answer into mcp_server_health_check. structuredContent is checked for presence, not validated against outputSchema.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/mcp_server_evaluate","outputSchema":{"type":"object","properties":{"verdict":{"type":"string"},"score":{"type":["number","null"]},"endpoint":{"type":"string"},"server":{"type":"object"},"checks":{"type":"array"},"latency":{"type":["object","null"]}},"additionalProperties":true},"guidance":{"gate":"signal-only","prefer":"gate on the reproducible sub-checks (manifest discovery, schema shape, JSON-RPC call) rather than on the aggregate PASS/FIX/BLOCK — the latency percentiles are non-deterministic"}},{"name":"toxicity_scan","category":"qa","description":"Scan text for toxic language, hate speech, bias/stereotype framing, violence, sexual and self-harm content. Lexical + structural pattern matching (identity term + predicate), not a semantic classifier — returns per-category risk plus the named rules that fired, so every finding can be checked. Useful for LLM safety guardrail testing and triage; signal-only, not a calibrated CI gate.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/toxicity_scan","outputSchema":{"type":"object","properties":{"overall_risk":{},"categories_checked":{"type":"number"},"results":{},"text_length":{"type":"number"},"method":{"type":"string"}},"additionalProperties":true},"guidance":{"gate":"signal-only","prefer":"a calibrated classifier for a hard CI gate"}},{"name":"function_call_validate","category":"qa","description":"Validate an LLM function call / tool_use output: check that function name is in allowed list, arguments match expected schema, no extra/missing args. For OpenAI function calling & MCP tool_use testing.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/function_call_validate","outputSchema":{"type":"object","properties":{"valid":{"type":"boolean"},"errors":{"type":"array"},"function_name":{},"provided_args":{},"required_args":{},"error_count":{"type":"number"}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"mcp_schema_lint","category":"qa","description":"Lint an MCP tool definition for best practices: naming conventions, description quality, schema completeness, required fields consistency, description length. Returns actionable warnings.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/mcp_schema_lint","outputSchema":{"type":"object","properties":{"quality_score":{},"grade":{},"errors":{},"warnings":{},"error_count":{"type":"number"},"warning_count":{"type":"number"}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"bias_detect","category":"qa","description":"Analyse a set of LLM responses generated from the same prompt template but with different demographic variants (gender, origin, age, tone). Returns a bias score (0-100), sentiment analysis per variant, pairwise Jaccard similarity, and a human-readable verdict. No API key needed — runs entirely locally.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/bias_detect","outputSchema":{"type":"object","properties":{"biasScore":{"type":"number"},"verdict":{"type":"string"},"avgSimilarity":{"type":"number"},"minSimilarity":{"type":"number"},"sentimentVariance":{"type":"number"},"lengthCV":{"type":"number"},"sentiments":{"type":"array","items":{"type":"object","properties":{"variantId":{"type":"string"},"positive":{"type":"number"},"negative":{"type":"number"},"ratio":{"type":"number"}}}},"pairwiseSimilarities":{"type":"array","items":{"type":"object","properties":{"a":{"type":"string"},"b":{"type":"string"},"score":{"type":"number"}}}}},"additionalProperties":true},"guidance":{"gate":"signal-only","prefer":"gate on the reproducible sub-metrics it returns (minSimilarity, lengthCV, sentimentVariance) rather than on the aggregate biasScore/verdict — the score blends a hand-rolled sentiment lexicon with Jaccard word overlap, neither calibrated"}},{"name":"shield_analyze","category":"security","description":"Run a comprehensive AI guardrail analysis on an LLM response. Orchestrates 7 deterministic safety checks plus an optional LLM-powered deep analysis in parallel: hallucination detection (grounding score), prompt injection scan on BOTH the response and the original prompt (reported separately as checks.injection / checks.injection_prompt, scored once at the worse of the two), toxicity scan, output validation (PII/safety), guardrail rules, response quality scoring, and AI verdict (via Qwen, Gemma, Llama, etc.). Returns a unified PASS/FIX/BLOCK verdict with a 0-100 safety score, per-check results, and actionable fix recommendations. PII gates the verdict: an SSN or credit card in the response forces BLOCK, an email forces FIX, phone/IP matches are flagged only (their regexes also match dates and version strings). Use this as a single-call safety gate before surfacing any LLM output to users.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/shield_analyze","outputSchema":{"type":"object","properties":{"verdict":{},"score":{},"grade":{},"flags":{},"checks":{"type":"object"}},"additionalProperties":true},"guidance":{"gate":"signal-only","prefer":"gate on the sub-checks you can reproduce (checks.safety pii_scan, guardrail rules) rather than on the aggregate verdict — the score blends regex heuristics with an optional LLM judge"}},{"name":"security_headers_check","category":"security","description":"Analyse the HTTP security headers of a public URL OR of raw response headers you paste in. Grades each header (A–F) for: Strict-Transport-Security, Content-Security-Policy, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, X-XSS-Protection, Cross-Origin-Opener-Policy, Cross-Origin-Resource-Policy, and Cross-Origin-Embedder-Policy. Returns an overall score (0–100), per-header grades, missing headers, and fix snippets for Express, Nginx, and Apache. For localhost/private targets the remote server cannot reach, pass the `headers` parameter instead of `url`.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/security_headers_check","outputSchema":{"type":"object","properties":{"header":{},"key":{},"value":{},"grade":{},"weight":{},"fix":{},"url":{},"source":{},"score":{},"overall_grade":{},"headers_checked":{"type":"number"},"missing_count":{"type":"number"},"weak_count":{"type":"number"},"missing":{},"weak":{},"details":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"ssl_certificate_check","category":"security","description":"Analyse the SSL/TLS certificate of any HTTPS host. Returns certificate subject, issuer, validity dates, days until expiry, protocol version, cipher suite, key exchange info, and an overall grade (A+, A, B, C, F). Detects expired, self-signed, and weak certificates. Use this to audit TLS posture before production deployment or during security reviews.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/ssl_certificate_check","outputSchema":{"type":"object","properties":{"host":{"type":"string"},"grade":{"type":"string"},"subject":{"type":"object"},"issuer":{"type":"object"},"valid_from":{"type":"string"},"valid_to":{"type":"string"},"days_until_expiry":{"type":"number"},"is_expired":{"type":"boolean"},"is_self_signed":{"type":"boolean"},"protocol":{"type":"string"},"cipher":{"type":"object"},"issues":{"type":"array","items":{"type":"string"}}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"cors_test","category":"security","description":"Test a URL for CORS misconfigurations. Sends preflight (OPTIONS) requests with various Origin headers to detect: wildcard origins with credentials, origin reflection (echoing any origin), null origin acceptance, subdomain wildcard bypass, and missing Vary headers. Returns risk level (safe/low/medium/high/critical) plus per-origin results. \"unknown\" means nothing was actually tested — every origin either failed to connect or answered 5xx, so the target returned no CORS decision; never read it as \"safe\". A 4xx preflight IS a real result (the server refused it and a browser would fail closed).","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/cors_test","outputSchema":{"type":"object","properties":{"url":{},"risk_level":{"enum":["safe","low","medium","high","critical","unknown"]},"origins_tested":{"type":"number"},"origins_reachable":{"type":"number"},"origins_conclusive":{"type":"number"},"origins_inconclusive":{"type":"number"},"total_findings":{"type":"number"},"warning":{"type":"string"},"error":{"type":"string"},"tests":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"cors_checker","category":"security","description":"Check the CORS configuration of a URL the same way a browser would. Returns the main response status, all Access-Control-* headers, the tested origin, and the preflight OPTIONS response. Use this for direct CORS debugging, not just security auditing.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/cors_checker","outputSchema":{"type":"object","properties":{"url":{},"status":{},"testedOrigin":{},"method":{},"corsHeaders":{},"allHeaders":{},"preflight":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"cookie_security_audit","category":"security","description":"Audit the security attributes of cookies set by any URL. Fetches the URL and inspects all Set-Cookie headers for: HttpOnly, Secure, SameSite, Domain scope, Path scope, Max-Age/Expires, __Host-/__Secure- prefixes. Flags insecure patterns: missing HttpOnly on session cookies, missing Secure flag, SameSite=None without Secure, overly broad Domain, and excessive TTL. Returns per-cookie grades and an overall security score (0–100) — the score is the WEAKEST cookie, not the average, so one leaking session cookie cannot be averaged into a green result (average_score is reported separately).","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/cookie_security_audit","outputSchema":{"type":"object","properties":{"url":{},"cookies_found":{"type":"number"},"score":{"type":"number"},"message":{"type":"string"},"cookies":{"type":"array"},"name":{},"httpOnly":{},"secure":{},"sameSite":{},"domain":{},"path":{},"max_age":{},"host_prefix":{},"secure_prefix":{},"issues":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"web_security_audit","category":"security","description":"Run a comprehensive web security audit combining headers, SSL, CORS, and cookies checks — then use an LLM to produce a prioritised remediation plan. Orchestrates security_headers_check + ssl_certificate_check + cors_test + cookie_security_audit in parallel, merges all findings, then asks an AI model to: (1) rank vulnerabilities by real-world exploitability, (2) generate a remediation roadmap, (3) produce fix code snippets for the detected stack. Returns both raw audit data and the AI analysis. Use this as a one-click security posture assessment.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/web_security_audit","outputSchema":{"type":"object","properties":{"header":{},"key":{},"value":{},"grade":{},"weight":{},"fix":{},"url":{},"score":{},"overall_grade":{},"headers_checked":{"type":"number"},"missing_count":{"type":"number"},"weak_count":{"type":"number"},"missing":{},"weak":{},"details":{},"risk_level":{},"origins_tested":{"type":"number"},"total_findings":{"type":"number"},"tests":{},"cookies_found":{"type":"number"},"message":{"type":"string"},"cookies":{"type":"array"},"name":{},"httpOnly":{},"secure":{},"sameSite":{},"issues":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"rate_tool","category":"meta","description":"Give honest usage feedback on an IA-QA MCP tool. Provide a score (1-5) and a comment. Rate low (1-2) if the tool was wrong, irrelevant, or a poor fit; rate high (4-5) only if it genuinely solved your need. Ratings are aggregated on a public dashboard at /devtools/mcp-ratings. Skip rating routine successes — we want signal, not praise. Example: rate_tool({ tool_name: \"format_json\", score: 2, comment: \"Tried to pretty-print a JSON5 file, it rejected trailing commas — not usable for my case.\" })","annotations":{"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/rate_tool","outputSchema":{"type":"object","properties":{"ok":{"type":"boolean"},"tool_name":{},"score":{},"comment":{},"truncated":{"type":"boolean"},"stored_chars":{"type":"number"},"rated_at":{"type":"string"},"message":{"type":"string"}},"additionalProperties":true}},{"name":"decode_jwt","category":"dev","description":"Decode a JWT (JSON Web Token) and return its header and payload without verifying the signature. Also reports whether the token is expired and the exact expiry date. Use to inspect claims (sub, iss, exp, roles) during debugging or when integrating with an auth provider.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/decode_jwt","outputSchema":{"type":"object","properties":{"header":{},"payload":{},"expired":{},"expiresAt":{},"note":{"type":"string"}},"additionalProperties":true}},{"name":"validate_url","category":"dev","description":"Parse and validate a URL. Returns decomposed components: protocol, hostname, port, path, query parameters, hash, and origin.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/validate_url","outputSchema":{"type":"object","properties":{"valid":{"type":"boolean"},"protocol":{},"hostname":{},"port":{},"pathname":{},"search":{},"query_params":{},"hash":{},"origin":{},"full":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"http_status_lookup","category":"dev","description":"Look up detailed information about any HTTP status code: class, name, description, cacheability, typical causes, and handling best practices. Covers every code in the IANA HTTP Status Code Registry (1xx-5xx, including 226, 425, 451, 508, 511 and the WebDAV codes) with its defining RFC; anything outside the registry is reported as `registered: false` rather than described. `cacheable` means heuristically cacheable by default per RFC 9110 §15.1.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/http_status_lookup","outputSchema":{"type":"object","properties":{"code":{},"class":{},"name":{"type":"string"},"desc":{"type":"string"},"cacheable":{},"registered":{"type":"boolean"},"description":{}},"additionalProperties":true}},{"name":"parse_http_headers","category":"dev","description":"Parse a raw HTTP headers block into a structured JSON object. Detects multi-value headers, masks Authorization values, and optionally audits for missing security headers (HSTS, CSP, X-Frame-Options, etc.).","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/parse_http_headers","outputSchema":{"type":"object","properties":{"parsed":{"type":"object"},"header_count":{"type":"number"},"security":{"type":"object"}},"additionalProperties":true}},{"name":"detect_secrets","category":"dev","description":"Scan code or config files for hardcoded secrets: AWS keys, GitHub tokens, OpenAI/Anthropic API keys, Stripe secrets, JWTs, database connection strings, and generic passwords. Returns findings with severity. Run before every commit.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/detect_secrets","outputSchema":{"type":"object","properties":{"risk_level":{},"total_findings":{"type":"number"},"findings":{},"filename":{},"recommendation":{}},"additionalProperties":true},"guidance":{"gate":"deterministic"}},{"name":"latency_benchmark","category":"web","description":"Measure response time of one or more HTTP endpoints (GET/POST). Runs N iterations and returns min/max/avg/p95 latency. Useful for API and MCP server benchmarking.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"schema_url":"https://www.ia-qa.com/mcp/tool/latency_benchmark","outputSchema":{"type":"object","properties":{"results":{"type":"array","items":{"type":"object"}},"iterations":{"type":"number"}},"additionalProperties":true}},{"name":"hash_text","category":"encoding","description":"Compute a cryptographic hash of a text string. Use when you need to verify data integrity, generate content fingerprints, hash passwords (prefer SHA-256+), or produce a fixed-length digest of any input. Supports SHA-256 (default), SHA-512, SHA-1, and MD5.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/hash_text","outputSchema":{"type":"object","properties":{"hash":{},"algorithm":{},"input_length":{"type":"number"}},"additionalProperties":true}},{"name":"generate_password","category":"encoding","description":"Generate a cryptographically secure random password using crypto.randomBytes. Configurable length (4–128), uppercase letters, digits, and symbols. Use when resetting user passwords, seeding test accounts, or generating API secrets.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/generate_password","outputSchema":{"type":"object","properties":{"password":{},"length":{"type":"number"},"charset_size":{"type":"number"}},"additionalProperties":true}},{"name":"generate_hmac","category":"encoding","description":"Compute an HMAC signature for a message using a secret key. Supports SHA-256 (default), SHA-512, SHA-1, and MD5. Used for API request signing, webhook verification (GitHub, Stripe, Twilio), and JWT validation.","annotations":{"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"schema_url":"https://www.ia-qa.com/mcp/tool/generate_hmac","outputSchema":{"type":"object","properties":{"hmac":{},"algorithm":{},"encoding":{},"message_length":{"type":"number"}},"additionalProperties":true}}]}