MCP servers

Local procedural knowledge with spells, notes, and revision history.

Local tasks, calendar commitments, and recurring work.

Local-first privacy MCP server for sensitive AI workflows

MCP Server for understanding, managing & troubleshooting your GCP environment.

Non-custodial USDC wallet on Base with spending limits enforced in code, not in a prompt.

Abnormal Security MCP: threats, search, remediation, ATO cases, vendor/BEC, and evidence download.

MCP server for Openlane GRC: controls, evidence, policies, risks, workflows, and approvals.

Steam store/game data (no key) plus player profiles, libraries and achievements (Steam Web API).

Send and receive email, give agents mailboxes, and manage domains and templates with Groundmail.

Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure

Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs

Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit

OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks

CVE scanning for npm/pip/cargo dependencies via OSV

DNS record enumeration, misconfiguration and dangling-subdomain detection

MCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs

Scans agent code for untrusted input poisoning persistent cross-session memory

Unified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF

Audits shipped apps for how easily they can be reverse engineered

Baselines an MCP server's tools and detects tool-definition changes after approval

Scans files for leaked secrets and API keys

Checks declared npm/PyPI dependencies against real registries to catch slopsquatting

TLS certificate/cipher/protocol inspection

Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress