Search excessionlabs.ai, the site of Excession Labs, a security lab, and request a security test.
Scored across 4 tools
Each tool has a clearly distinct role: discovery (search_site), retrieval (get_page), informational contact details (how_to_contact), and a transactional action (request_security_test). The only overlap is that how_to_contact mentions request_security_test, but the descriptions make the info-vs-action boundary explicit.
All names are snake_case and mostly verb-first (get_page, search_site, request_security_test), giving a readable pattern. how_to_contact deviates from the verb_noun convention, which is a minor inconsistency.
Four tools is well-scoped for a small site-search plus lead-request server; each tool covers a distinct step (search, read, contact info, submit request). Nothing feels padded or missing at the count level.
The surface covers the core lifecycle: find pages, read them, learn contact options, and submit a security test request with clear prerequisites. Minor gaps exist—no way to check the status of a submitted request or enumerate all pages beyond search—but agents can work around these via llms.txt and search_site.
Read one public page of excessionlabs.ai as Markdown. Use a path from search_site or llms.txt.
Inputs: path (required).
Return the ways a person can contact Excession Labs: the request form, email, and the request_security_test tool for agents.
Inputs: no named parameters.
Send a request for a security test (web application, API, multi-tenant SaaS isolation or AI application) to Excession Labs on behalf of a person who asked for it. Needs an agent key (POST https://excessionlabs.ai/agent/auth, then Authorization: Bearer ). Excession Labs replies to the person by email to agree scope; testing starts only after a written scope and written authorization from the system owner. Never include passwords, API keys or customer data. Limits: 5 requests a day per key, 3 a day per email address.
Inputs: name (required), email (required), targets (required), test_type (required), +7 more.
Search the public pages and research notes on excessionlabs.ai. Returns titles, URLs and one-line summaries.
Inputs: query (required), limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Read AI security guides and lab research, and request an LLM or AI agent security assessment.
Test your AI agents for security and safety weaknesses, and re-verify the fixes.
Scan websites and code for security, performance and SEO issues from your AI assistant.
Authorized security scans, evidence, fix prompts and retests for AI-built web apps.
Add one secure layer between your agents and this server.
