mitmproxy-mcp MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UV_PUBLISH_TOKEN | No | PyPI token for publishing the package | |
| UV_PUBLISH_PASSWORD | No | PyPI password for publishing the package | |
| UV_PUBLISH_USERNAME | No | PyPI username for publishing the package |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_flowsC | Retrieves detailed HTTP request/response data including headers, content (or structure preview for large JSON), and metadata from specified flows |
| get_flow_detailsC | Lists HTTP requests/responses from a mitmproxy capture session, showing method, URL, and status codes |
| extract_json_fieldsC | Extract specific fields from JSON content in a flow using JSONPath expressions |
| analyze_protectionC | Analyze flow for bot protection mechanisms and extract challenge details |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
The tools have some overlap that could cause confusion. 'get_flow_details' and 'list_flows' both retrieve HTTP flow data, with 'get_flow_details' focusing on method/URL/status and 'list_flows' providing headers/content/metadata—these boundaries are unclear and might lead to misselection. However, 'analyze_protection' and 'extract_json_fields' are clearly distinct, targeting bot protection analysis and JSON field extraction respectively.
The naming is mostly consistent with a verb_noun pattern, using snake_case throughout. 'analyze_protection', 'extract_json_fields', and 'list_flows' follow this well, but 'get_flow_details' deviates slightly by using 'get' instead of a more descriptive verb like 'show' or 'retrieve', which is a minor inconsistency in an otherwise predictable set.
With 4 tools, the count is well-scoped for a mitmproxy server focused on HTTP flow analysis. Each tool appears to serve a distinct purpose within this domain, such as listing flows, analyzing protections, and extracting data, making the set neither too sparse nor overloaded for the intended functionality.
The tool surface has notable gaps for a mitmproxy domain. It covers flow retrieval, protection analysis, and JSON extraction, but lacks operations for modifying or intercepting flows (e.g., add, edit, block), which are core to proxy functionality. Agents can work around this by using existing tools for analysis, but the absence of manipulation tools limits completeness.