Fiddler Everywhere MCP Server
Fiddler Everywhere ships a first-party Model Context Protocol server that lets a coding agent drive the locally installed proxy: start browser/terminal/ network captures, read captured sessions and full request/response details, apply filters, create traffic-rewriting rules, manage a reverse proxy, and cache LLM agent calls. The server is hosted BY the desktop application on the loopback interface — it is not a hosted, internet-reachable endpoint.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport streamable-http (loopback)
Tools
get_status— Gets the current status of Fiddler, including IsUserLoggedIn, IsRootCertificateTrusted, number of Browser and Terminal instances running, reverse proxy status and configured ports, IsSystemProxyEnabled, IsNetworkCaptureEnabled, and the number of captured and visible sessions.is_user_logged_in— Indicates whether Fiddler is currently authenticated.initiate_login— Performs login to Fiddler. Opens a new Chrome window for authentication.open_trust_root_certificate_dialog— Opens the system trust root certificate dialog. Required for HTTPS traffic interception.start_capture_with_browser— Opens a fresh Chrome-based browser instance with Fiddler proxy settings applied.start_capture_with_terminal— Starts a new terminal with Fiddler proxy settings applied.capture_application— Starts network-level traffic capture scoped to a specific application. Accepts an optional process name or PID; auto-detects the target from the active IDE or CLI context when omitted.get_sessions— Gets the sessions from the specified Fiddler sessions source with active filters applied. LiveTraffic for captured HTTP/HTTPS traffic, AgentCalls for LLM agent API calls.get_sessions_count— Gets the number of sessions in the specified Fiddler sessions source.get_session_details— Gets detailed information about a specific session, including request and response headers, bodies, HTTP method, URL, status code, protocol, start time, duration, client and remote HTTP versions, TLS versions and IPs.apply_filters— Applies filters to the specified sessions source. Applying filters wipes all existing filters; call with an empty filter collection to clear.clear_sessions— Clears all sessions in the specified Fiddler sessions source.cache_agent_calls— Enables or disables caching for a specific session in the Agent Calls section.check_cache_status— Checks whether a specific session in the Agent Calls section is currently cached.create_rule— Creates a rule to modify sessions in Fiddler, applied to all sessions matching the specified criteria. At least one condition must be specified.clear_rules— Clears all rules created from the MCP server.add_reverse_proxy_port— Adds a reverse proxy configuration forwarding requests from a local port to a remote host and intercepting the traffic in between.remove_reverse_proxy_port— Removes a reverse proxy configuration for a specific port.enable_reverse_proxy— Enables the reverse proxy.disable_reverse_proxy— Disables the reverse proxy.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.