3433 Model Context Protocol servers — searchable, rated, ready to install.
Identity and authorization in one system: allow, deny, the reason, and a record.
Multi-account Google Workspace MCP server: 942 tools, 29 services, discover-first, BYO OAuth.
Licensed NY cannabis dispensaries, brands, deals, license checks and lab-anchored reviews. No auth.
CERT-FR (ANSSI) security advisories & alerts: French national CERT vulnerability feed, hourly
Check a Slack webhook URL shape. Secret discarded.
Local MCP tools that keep secrets out of agent context: redact files, scan commits, verify webhooks.
Pre-action authorization for AI agents: permit, deny or escalate against a signed delegation chain.
Meaning of HTTP 511.
B2B company and contact data for lead lists, enrichment, research, and outreach. OAuth sign-in.
Authorizes MCP tool calls against a session policy, not one call at a time.
Dapr state, pub/sub, bindings, secrets, locks, crypto, conversation, actors, invocation as MCP tools
Verified records on 60 niche fashion subcultures for AI agents, $0.01 per lookup over x402
Private, local search over your own files, by meaning and keywords, with secrets redacted.
Free-trial AI fleet spend meter. 100 calls or 14 days. No auth.
Company filing/CVE snapshots, status and optional feedback. Remote MCP or local stdio. Free Phase A.
FCA UK short-position disclosures — the Financial Conduct Authority (fca.org.uk) publishes a daily…
Token guard and rate limiter preventing runaway API cost spikes for OpenAI and Anthropic.
Find and fix drift between Supabase environments: schema, RLS, roles, auth, storage and more.
Read-only visual Hyperliquid carry scan via MCP Apps and x402 v2 Solana USDC.
Read-only tools for AI agents: who can change a smart contract, how fast. Signed data, testnet.
Turn URLs, PDFs and DOCX into clean Markdown for agents, plus prompt-injection scanning
Deploy AI-built internal apps behind your company login, with a database, files and secrets.
Passive AppSec scanners as eight parameterless MCP tools; the audited repository is data.
Actively exploited? End of life? Which version fixes it? CVE verdicts for server software.
POST /mcp