"Habr" matching MCP servers:

Gates agent tool execution with human approval, audit trails, and replay-resistant permits, enabling safe use of tools in agent loops.

Audits HAR captures locally with MCP tools for triage, findings, vendor blast radius, CSP generation, and sanitization—no network calls, redacted by default.

Professional MCP server for HAR (HTTP Archive) network captures, enabling AI agents to extract endpoints, detect secrets, generate code, and export to Postman/OpenAPI.

Enables analysis of large HAR files with schema-less protobuf/gRPC decoding, allowing structured queries and decoding of opaque binary bodies for reverse-engineering and traffic research.

A Python MCP server that loads and analyzes HAR files locally, providing structured summaries to AI assistants to avoid token explosion and sensitive content filtering.

Enables AI agents to locally parse and analyze HAR files through read-only MCP tools, including searching requests, discovering endpoints, tracing values, detecting auth and API patterns, comparing requests, and exporting redacted cURL commands.

Captures website HAR data via headless Chromium and provides 20 tools for performance/security auditing, API reverse engineering, and code generation.

Enables querying and searching the Japanese Address Base Registry (ABR) data definitions and official documentation, including field definitions, datasets, and policy documents through tools like list_datasets, get_dataset, search_field, and search_docs.