# Jcjamet Ia Qa Security MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.jcjamet%2Fia-qa-security
Registry id: `mcp-registry/io.github.jcjamet/ia-qa-security`
Status: live (checked 2026-11-22T20:39:38.214Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 870
- Outages (90 days): 0

## Install

```json
{
  "mcpServers": {
    "jcjamet-ia-qa-security-mcp-server": {
      "type": "http",
      "url": "https://www.ia-qa.com/mcp/security"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http jcjamet-ia-qa-security-mcp-server https://www.ia-qa.com/mcp/security
```

## Tools (31)

- `agent_checkout_eval`: Judges a shopping agent's run in Sandbox Bazaar, a fictional shop whose scenarios hide known traps (injected instructions, last-step fees, pre-checked subscript
- `bias_detect`: 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
- `cookie_security_audit`: 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
- `cors_checker`: 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
- `cors_test`: Audit a URL for CORS misconfigurations across several origins: wildcard with credentials, reflected origin, null origin, subdomain bypass, missing Vary. Returns
- `decode_jwt`: 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 
- `detect_secrets`: Scan code or config files for hardcoded secrets: AWS keys, GitHub tokens, OpenAI/Anthropic API keys, Stripe secrets, JWTs, Slack/Teams/Discord webhook URLs, ses
- `find_tool`: Search available MCP tools by keyword or category before calling them. Returns names, descriptions and, on request, inputSchemas. Queries are logged 90 days, sc
- `function_call_validate`: 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/m
- `generate_hmac`: 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 verificat
- `generate_password`: Generate a cryptographically secure random password using crypto.randomBytes. Configurable length (4–128), uppercase letters, digits, and symbols. Use when rese
- `guardrail_test`: Test an LLM response against a set of guardrail rules: must-include, must-not-include, max length, required format, language, forbidden patterns, and custom reg
- `hash_text`: 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 p
- `http_status_lookup`: Look up detailed information about any HTTP status code: class, name, description, cacheability, typical causes, and handling best practices. Covers every code 
- `latency_benchmark`: Measure response time of one or more HTTP endpoints (GET/POST). Runs N iterations and returns min/max/avg/p95 latency.
- `mcp_schema_lint`: 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 ref
- `mcp_server_evaluate`: 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, erro
- `mcp_server_health_check`: Check an MCP server's tool definitions without contacting it (undeployed, stdio, CI). Input: a tools/list answer (JSON-RPC or its result), an array of tools, on
- `parse_http_headers`: Parse a raw HTTP headers block into a structured JSON object. Detects multi-value headers, masks Authorization values, and optionally audits for missing securit
- `prompt_injection_scan`: Scan user input or prompts for prompt injection patterns. Pattern-based: it recognises known phrasings and structures, not intent — an uncovered paraphrase or l
- `rate_tool`: 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
- `redact_pii`: Automatically detect and redact Personally Identifiable Information (PII) from text. Replaces emails, phone numbers, SSNs, IBANs, credit cards, IP addresses, an
- `secret_scan`: Scan text or code for leaked secrets: API keys (AWS, GCP, Azure, OpenAI, Anthropic, Stripe, GitHub, GitLab, Slack, Twilio, SendGrid, HuggingFace), Slack / Teams
- `security_headers_check`: 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-Secu
- `shield_analyze`: One-call safety gate for an LLM response: injection on the response, prompt and source, toxicity, PII, grounding (with source), guardrail rules, plus an LLM rev
- `ssl_certificate_check`: Analyse the SSL/TLS certificate of any HTTPS host. Returns certificate subject, issuer, validity dates, days until expiry, protocol version, cipher suite, key e
- `toxicity_scan`: Scan text for toxic language, hate speech, bias/stereotype framing, violence, sexual and self-harm content. Lexical + structural pattern matching (identity term
- `validate_agent_trajectory`: Run declarative assertions on an agent trace (OpenAI tool calls, Anthropic tool_use, LangChain run trees, ReAct logs). Deterministic, no LLM. Assertions: order 
- `validate_mcp_response`: 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 JSO
- `validate_url`: Parse and validate a URL. Returns decomposed components: protocol, hostname, port, path, query parameters, hash, and origin.
- `web_security_audit`: Web security audit: security_headers_check + ssl_certificate_check + cors_test + cookie_security_audit in parallel, one grade capped by the weakest link. Determ

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
