Blitz Strike
MCP ServerA penetration-testing methodology delivered as one MCP server: BLITZ maps the attack surface, EAGLE-EYE traces source-to-sink, STRIKE live-verifies every finding before it is reported.
- mcp-server
- security
- pentest
- methodology
Linear's hosted MCP server for issues, projects, and comments — OAuth, no local install.
Linear's first-party hosted MCP server at mcp.linear.app/mcp. Gives Claude read-write access to issues, projects, cycle data, and comments, with a dedicated read-only endpoint variant. Authentication is OAuth 2.1 with dynamic client registration, so setup is a link-and-approve flow rather than an API token. The official way to drive Linear from Claude Code or any MCP-aware agent.
Let Claude triage a Linear backlog, turn a planning doc into structured issues, or post standup updates — without leaving the editor. Use the readonly endpoint when Claude should never write.
Claude Code:
claude mcp add --transport http linear-server https://mcp.linear.app/mcp
then run /mcp in a session to complete OAuth.
Other clients (Cursor/VS Code/Zed/etc.):
{
"linear": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.linear.app/mcp"]
}
}The default `/mcp` endpoint is read-write — anything the authenticated Linear user can do, the agent can attempt. Prefer `/mcp/readonly` or the `read` OAuth scope for untrusted workflows. Codex needs `experimental_use_rmcp_client = true` in config.toml.
Charted
A penetration-testing methodology delivered as one MCP server: BLITZ maps the attack surface, EAGLE-EYE traces source-to-sink, STRIKE live-verifies every finding before it is reported.
Red Hat's "ripgrep for AI context" — a C++23 zero-dependency CLI that also speaks MCP.
One shared session memory for 25+ coding agents — Claude Code, Codex, and Cursor finally remember the same project.