RequestRepo MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@RequestRepo MCPlist the most recent HTTP requests captured"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RequestRepo MCP
MCP server for requestrepo by adragos.
Scope
Full requestrepo tool surface (requests, sharing, DNS, files, ping)
Default
stdiotransport, optionalstreamable-httpConfirm-gated mutations (
confirm=true)JSON-safe bytes envelope for binary fields
Full parameter docs are in TOOLS.md.
Related MCP server: MCP HTTP Client Server
Install
python -m pip install -e .For local development:
python -m pip install -e ".[dev]"Configuration
REQUESTREPO_TOKEN(optional)REQUESTREPO_ADMIN_TOKEN(optional)REQUESTREPO_HOST(defaultrequestrepo.com)REQUESTREPO_PORT(default443)REQUESTREPO_PROTOCOL(defaulthttps)REQUESTREPO_VERIFY(defaulttrue)REQUESTREPO_DEFAULT_TIMEOUT_SECONDS(default30)REQUESTREPO_MAX_BYTES(default65536)
Auth behavior:
If
REQUESTREPO_TOKENis set, it is used.Otherwise a new session is created, optionally with
REQUESTREPO_ADMIN_TOKEN.
Run
requestrepo-mcp --transport stdiorequestrepo-mcp --transport streamable-http --host 127.0.0.1 --port 8000 --streamable-http-path /mcpInstall In AI Clients
Codex
With token (optional, recommended if you already have one):
codex mcp add requestrepo --env REQUESTREPO_TOKEN=your-token -- requestrepo-mcp --transport stdioWithout token (creates a new session automatically):
codex mcp add requestrepo -- requestrepo-mcp --transport stdioCheck config:
codex mcp get requestrepoAutostart note:
Codex starts
stdioservers automatically.If startup fails, register with an absolute executable path:
codex mcp add requestrepo --env REQUESTREPO_TOKEN=your-token -- /absolute/path/to/requestrepo-mcp --transport stdioClaude Code / Claude Desktop
{
"mcpServers": {
"requestrepo": {
"command": "requestrepo-mcp",
"args": ["--transport", "stdio"],
"env": {
"REQUESTREPO_TOKEN": "your-token"
}
}
}
}Cursor
{
"mcpServers": {
"requestrepo": {
"command": "requestrepo-mcp",
"args": ["--transport", "stdio"],
"env": {
"REQUESTREPO_TOKEN": "your-token"
}
}
}
}VS Code (Copilot Agent)
.vscode/mcp.json:
{
"servers": {
"requestrepo": {
"type": "stdio",
"command": "requestrepo-mcp",
"args": ["--transport", "stdio"],
"env": {
"REQUESTREPO_TOKEN": "your-token"
}
}
}
}Tool Summary
session_infolist_requestswait_for_requestdelete_requestdelete_all_requestsshare_requestget_shared_requestlist_dnsadd_dnsremove_dnsupdate_dnslist_filesget_fileset_fileupdate_filesping
Mutation tools require confirm=true.
Testing
pytest -qCI runs tests on push and pull requests (see .github/workflows/ci.yml).
Available Tools
16 toolsadd_dnsC
Add a DNS record.
Inputs: domain (required), record_type (required), value (required), confirm (required). Returns: object
delete_all_requestsB
Delete all requests for the current session.
Inputs: confirm (required). Returns: object
delete_requestC
Delete one request.
Inputs: request_id (required), confirm (required). Returns: object
get_fileC
Get one file response.
Inputs: path (required), decode_base64, max_bytes. Returns: object
list_dnsB
List DNS records.
Inputs: no named parameters. Returns: object
list_filesB
List all file responses.
Inputs: no named parameters. Returns: object
list_requestsC
List captured requests with optional filtering.
Inputs: limit, offset, request_type, include_raw, +2 more. Returns: object
pingB
Ping the underlying requestrepo websocket connection.
Inputs: no named parameters. Returns: object
remove_dnsB
Remove DNS records by domain and optional type.
Inputs: domain (required), record_type, confirm. Returns: object
session_infoB
Return session info for the active requestrepo client.
Inputs: include_token. Returns: object
set_fileD
Set one file response.
Inputs: path (required), confirm (required), body_text, body_base64, +2 more. Returns: object
update_dnsC
Replace the full DNS records set.
Inputs: records (required), confirm (required). Returns: object
update_filesC
Replace all file responses.
Inputs: files (required), confirm (required). Returns: object
wait_for_requestC
Poll for a new request until timeout.
Inputs: request_type, timeout_seconds, poll_interval_seconds, include_raw, +2 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
TDQS
Scored across 16 tools
Most tools have distinct purposes, but some potential confusion exists between 'delete_request' and 'delete_all_requests', and 'set_file' and 'update_files' could overlap. The DNS tools (add_dns, list_dns, remove_dns, update_dns) are clearly differentiated by action, and file/request tools generally target different operations.
All tools follow a consistent verb_noun naming pattern with snake_case throughout. Examples include 'add_dns', 'list_requests', 'update_files', and 'wait_for_request'. There are no deviations in style or convention across the set.
With 16 tools, the count is slightly high but reasonable for a server handling requests, DNS, and files. It covers multiple domains without being excessive, though it might feel heavy compared to simpler servers. The tools appear well-scoped to the server's purpose.
The tool set provides good coverage for request management (list, delete, share, wait), DNS operations (add, list, remove, update), and file handling (get, list, set, update). Minor gaps include no explicit 'get_request' tool and limited session management beyond 'session_info', but agents can work around these with existing tools.
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseAqualityFmaintenanceAn MCP server that enables AI assistants to control HTTP Toolkit for intercepting, inspecting, and debugging HTTP(S) traffic from browsers, mobile devices, and Docker containers. It provides tools for server management, interceptor activation, and sending HTTP requests through natural language commands.2318 npm1MIT
- AlicenseNot gradedqualityDmaintenanceA powerful MCP server for making HTTP requests, GraphQL queries, and TCP/Telnet connections from AI assistants.7MIT
- AlicenseNot gradedqualityCmaintenanceMCP tool server that gives any AI agent the ability to search, scrape, and analyze content across the internet.42MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that enables AI agents to intercept, inspect, and modify HTTP traffic, with tools for searching, filtering, and managing captured requests and interceptors.11 npm8MIT