Summarize and search coding sessions, extract rules from discoveries, benchmark coding agents.
Summarize and search coding sessions, extract rules from discoveries, benchmark coding agents.
Extract rules from what worked. Track what didn't. Find the best models for your stack.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"afterpaths": {
"command": "uvx",
"args": ["afterpaths"],
"env": {
"ANTHROPIC_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Standalone MCP server bringing Warp™ Oz™ agents to Claude Code, Cursor, Codex and any MCP client — no VS Code required. Independent project, not
Defensive vulnerability intelligence search across public CVE/NVD and GitHub advisory APIs with CVSS
Read-only context and complete checks against patterns learned from git history. Local; no LLM.
Pay-per-call x402 MCP tools on Base USDC: Release Guardian + Workflow Runner.