IA-QA Security — 30 tools
Server Details
Agent security: prompt injection, PII & secret scans, TLS/header/CORS audits, MCP checks. Free.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- ia-qa-com/mcp
- GitHub Stars
- 0
- Server Listing
- IA-QA MCP server
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 30 tools
Most tools target a distinct security concern, but several near-duplicate pairs blur boundaries: detect_secrets vs secret_scan (both scan code for hardcoded keys with the same finding format), security_headers_check vs parse_http_headers' optional security audit, and mcp_schema_lint vs mcp_server_health_check (single tool vs pasted tools/list). cors_checker vs cors_test and the validation cluster (guardrail_test, validate_mcp_response, validate_agent_trajectory, shield_analyze) are also easy to misselect without reading full descriptions, though the descriptions do state the split.
Everything is snake_case and readable, but the verb/noun convention is not fixed: verb_noun (detect_secrets, generate_hmac, decode_jwt, redact_pii), noun_verb (secret_scan, bias_detect, prompt_injection_scan), and bare nouns (cors_test, guardrail_test, http_status_lookup, latency_benchmark, rate_tool, find_tool) all coexist. Related tools often use different patterns (cors_checker vs cors_test, detect_secrets vs secret_scan), which weakens predictability.
At 30 tools this is above the heavy threshold, and the surface is inflated by functional duplicates (detect_secrets/secret_scan, cors_checker/cors_test, mcp_schema_lint/mcp_server_health_check, parse_http_headers/security_headers_check). The domain breadth is real (TLS, CORS, cookies, secrets, PII, injection, MCP validation), so it is not gratuitous padding, but consolidating the overlapping pairs would yield a tighter ~22-tool set.
Coverage of the stated web-security + LLM-safety QA domain is strong: passive URL audits (headers, TLS, CORS, cookies), secret/PII detection, injection and toxicity scanning, guardrails, crypto helpers, and MCP/agent-output validation, plus an orchestrating web_security_audit. Minor gaps remain: JWT is only decoded, never signature-verified; no XSS/CSRF/active vulnerability probing or directory/CI-wide batch scanning; no structured report export.
Available Tools
30 toolsbias_detectARead-onlyIdempotentInspect
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.
Inputs: responses (required). Returns: verdict, lengthCV, biasScore, sentiments, +4 more
cookie_security_auditARead-onlyInspect
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).
Inputs: url (required). Returns: url, name, path, score, +11 more
cors_checkerARead-onlyInspect
Would a browser on this origin be allowed to read this URL? Verdict allowed | blocked | unknown, the reason, and the header to add. Only GET and HEAD are really sent: other methods measure the preflight alone. Many origins at once: cors_test.
Inputs: url (required), method, origin, credentials, +1 more. Returns: fix, checks, reason, status, +4 more
cors_testARead-onlyInspect
Audit a URL for CORS misconfigurations across several origins: wildcard with credentials, reflected origin, null origin, subdomain bypass, missing Vary. Returns risk level (safe/low/medium/high/critical) plus per-origin results. "unknown" means nothing was tested: every origin failed to connect, answered 5xx, or was refused with no CORS header (a 404, a firewall); never read it as "safe".
Inputs: url (required), origin. Returns: url, error, tests, warning, +6 more
decode_jwtARead-onlyInspect
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.
Inputs: token (required). Returns: note, header, expired, payload, +1 more
detect_secretsBRead-onlyIdempotentInspect
Scan code or config files for hardcoded secrets: AWS keys, GitHub tokens, OpenAI/Anthropic API keys, Stripe secrets, JWTs, Slack/Teams/Discord webhook URLs, session cookies, database connection strings, and generic passwords. Returns findings with severity.
Inputs: input (required), filename. Returns: filename, findings, risk_level, recommendation, +1 more
find_toolARead-onlyIdempotentInspect
Search available MCP tools by keyword or category before calling them. Returns names, descriptions and, on request, inputSchemas. Queries are logged 90 days, screened for credentials and personal data. Categories: data, dev, encoding, eval, integrations, llm, meta, qa, rag, security, text, web.
Inputs: query (required), category, max_results, with_schema. Returns: hint, tool, count, query, +5 more
function_call_validateARead-onlyIdempotentInspect
Validate an LLM function call / tool_use output: check that function name is in allowed list, arguments match expected schema (types, enums, ranges), no extra/missing args. Reads the definitions as OpenAI (parameters), MCP (inputSchema) or Anthropic (input_schema) write them, or as plain required_args/optional_args; reads the call as arguments (object or JSON string), input (Anthropic tool_use) or an OpenAI {function:{…}} wrapper.
Inputs: function_call (required), allowed_functions (required). Returns: valid, errors, error_count, function_name, +2 more
generate_hmacARead-onlyIdempotentInspect
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.
Inputs: secret (required), message (required), encoding, algorithm. Returns: hmac, encoding, algorithm, message_length
generate_passwordARead-onlyInspect
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.
Inputs: length, numbers, symbols, uppercase. Returns: length, password, charset_size
guardrail_testBRead-onlyIdempotentInspect
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.
Inputs: rules (required), response (required). Returns: pass, rule, label, value, +6 more
hash_textARead-onlyIdempotentInspect
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.
Inputs: input (required), algorithm. Returns: hash, algorithm, input_length
http_status_lookupARead-onlyIdempotentInspect
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.
Inputs: code (required). Returns: code, desc, name, class, +3 more
latency_benchmarkARead-onlyInspect
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.
Inputs: endpoints (required), iterations. Returns: results, iterations
mcp_schema_lintARead-onlyIdempotentInspect
Lint one MCP tool definition with the same rules as mcp_server_health_check: errors break the MCP spec (FAIL), documentation_issues are what its strict mode refuses — a parameter without description or type (FIX, never an A) — and suggestions are style only (snake_case) and change nothing.
Inputs: tool_definition (required). Returns: grade, errors, warnings, error_count, +2 more
mcp_server_evaluateARead-onlyInspect
Check that a live MCP server over Streamable HTTP speaks the protocol, 2026-07-28 or earlier: handshake or server/discover, tools/list and its definitions, error codes, one tools/call, structuredContent against outputSchema, latency. Returns PASS/FIX/BLOCK with a 0-100 score, or INCONCLUSIVE (score null) when authorization is required. The verdict covers the PROTOCOL, never whether tools answer correctly: what_this_does_not_prove lists what was not measured. Called: only test_tool_name, or a tool annotated readOnlyHint: true. A refusal of invented arguments is not scored (tool_behaviour: refused_placeholder); pass test_tool_args to exercise the tool. Private addresses and stdio are out of reach: paste tools/list into mcp_server_health_check.
Inputs: url (required), test_tool_args, test_tool_name. Returns: scope, score, checks, server, +7 more
mcp_server_health_checkARead-onlyIdempotentInspect
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.
Inputs: manifest (required), strict. Returns: stats, total, checks, failed, +4 more
parse_http_headersARead-onlyIdempotentInspect
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.).
Inputs: headers (required), analyze_security. Returns: parsed, security, header_count
prompt_injection_scanARead-onlyIdempotentInspect
Scan user input or prompts for prompt injection patterns. Pattern-based: it recognises known phrasings and structures, not intent — an uncovered paraphrase or language reads clean, so clean is not proof of safety. Instruction overrides are covered in 11 languages (EN, FR, ES, DE, IT, PT, NL, RU, ZH, JA, AR), also after removing invisible characters, lookalike letters, spacing and leetspeak (marked obfuscated). Detects overrides, jailbreaks, role manipulation, encoding tricks, chat-template delimiters and fake role headers, template injection ({{…}}, ${…}) and requests to repeat the preceding context. A match inside quoted or fenced text is reported one level lower and marked quoted, never suppressed; a quote introduced by a live imperative keeps its severity.
Inputs: input (required), sensitivity. Returns: notes, detections, risk_level, sensitivity, +4 more
rate_toolADestructiveInspect
Give honest usage feedback on an IA-QA MCP tool. Give 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. Maintainers read ratings, one vote per agent and tool a month: comments and per-tool scores are not published, only the overall average and vote count. Comments are screened: one carrying a credential is not stored, personal data becomes placeholders — describe what happened, not what a model should do. Skip routine successes: 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." })
Inputs: score (required), tool_name (required), comment. Returns: ok, score, comment, message, +4 more
redact_piiARead-onlyIdempotentInspect
Automatically detect and redact Personally Identifiable Information (PII) from text. Replaces emails, phone numbers, SSNs, IBANs, credit cards, IP addresses, and JWT tokens with [REDACTED_TYPE] placeholders. Safe to use before logging or sending to an LLM.
Inputs: input (required), types, marker. Returns: clean, pii_found, replacements, redacted_text, +1 more
secret_scanARead-onlyIdempotentInspect
Scan text or code for leaked secrets: API keys (AWS, GCP, Azure, OpenAI, Anthropic, Stripe, GitHub, GitLab, Slack, Twilio, SendGrid, HuggingFace), Slack / Teams / Discord webhook URLs, private keys, JWTs, database connection strings, Bearer and Basic auth headers, and hard-coded values assigned to password/secret/token names (a value read at run time — Cypress.env(), os.getenv() — is not flagged). Returns findings with type, severity, line and a redacted preview. Regex-based, no network.
Inputs: input (required), types. Returns: summary, findings, risk_level, input_lines, +3 more
security_headers_checkARead-onlyInspect
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.
Inputs: url, headers. Returns: fix, key, url, weak, +12 more
shield_analyzeARead-onlyInspect
One-call safety gate for an LLM response: grounding (with source), prompt injection on the response AND the prompt (checks.injection / checks.injection_prompt), toxicity, PII, guardrail rules, quality, plus an LLM review on Groq (server key; model "none" skips it and sends nothing out). Returns PASS/FIX/BLOCK, a 0-100 safety score, per-check results and fixes. PII gates the verdict: SSN or card → BLOCK, email → FIX, phone/IP flagged only.
Inputs: response (required), model, rules, prompt, +1 more. Returns: flags, grade, score, checks, +1 more
ssl_certificate_checkARead-onlyInspect
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.
Inputs: host (required), port. Returns: host, grade, cipher, issuer, +8 more
toxicity_scanARead-onlyIdempotentInspect
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. Languages: English for every category; French for insults, coarse language, direct threats and self-harm intent; anything else reads clean, so clean is not proof of safety. Text is also matched after undoing leetspeak and lookalike letters. Self-harm is critical only on a first-person intent — a mention ("call 988 if you have suicidal thoughts") is medium. Useful for LLM safety guardrail testing and triage; signal-only, not a calibrated CI gate.
Inputs: text (required), categories. Returns: method, results, text_length, overall_risk, +1 more
validate_agent_trajectoryARead-onlyIdempotentInspect
Run declarative assertions on an agent trace (OpenAI tool calls, Anthropic tool_use, LangChain run trees, ReAct logs). Deterministic, no LLM. Assertions: order (tool A before B), must_call, must_not_call, max/min calls, no_error, recovery (a successful step after the last error), no_injection, no_pii. A step is errored when the trace marks it (is_error, status error/failed, success:false) or its text starts with Error:/Traceback — prose is never keyword-scanned. Verdict PASS / FAIL / INCONCLUSIVE (0 steps parsed, never PASS).
Inputs: trace (required), assertions (required), format. Returns: steps, results, summary, verdict, +1 more
validate_mcp_responseARead-onlyIdempotentInspect
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.
Inputs: response (required), min_items, expected_type, required_keys, +4 more. Returns: total, checks, failed, passed, +1 more
validate_urlARead-onlyIdempotentInspect
Parse and validate a URL. Returns decomposed components: protocol, hostname, port, path, query parameters, hash, and origin.
Inputs: input (required). Returns: full, hash, port, valid, +6 more
web_security_auditARead-onlyInspect
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.
Inputs: url (required), model, api_key. Returns: fix, key, url, name, +23 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Safety tools for AI agents: safe page reader, prompt-injection, secrets, PII and MCP server scans
LLM agent security scan: injection, jailbreak, tool abuse probes plus guardrail audit.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Related MCP Servers
- AlicenseAqualityDmaintenanceSecurity scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows.861 npmMIT
- AlicenseAqualityCmaintenanceSecurity co-pilot for AI agents. Scans for vulnerabilities like prompt injection, infinite loops, and token bombing in AI Agents, audits MCP servers, verifies AGENTS.md governance, and generates EU AI Act compliance reports.10109 npm3Apache 2.0
- AlicenseNot gradedqualityBmaintenanceMCP security scanner for AI agents - detects prompt injection, secrets, PII, and vets MCP servers before installation1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceFull-stack security for AI agents — static analysis + MCP runtime interception. 31 rules detect prompt injection, data exfiltration, backdoors, tool poisoning, and cross-file attack chains. Includes MCP proxy for real-time blocking, Python AST taint tracking, multi-language injection detection (8 languages), and AI-powered deep analysis. Free, offline, zero-config.83 npm16MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.