all-mcp
Optional Gemini routing backend for the ask tool: with a GEMINI_API_KEY (free tier, default model gemini-3.5-flash), the server uses Gemini to route a question to the correct child MCP server and tool, executes it, and returns the result with a routing trace and citation links.
Fully local routing backend for the ask tool (default model qwen2.5:7b on http://localhost:11434, selected via LLM_PROVIDER=[ollama](/mcp/servers/integrations/ollama)), letting the router pick the right server/tool and arguments with no API key and no data leaving the machine.
Optional routing backend for the ask one-step answering tool: when an [OPENAI](/mcp/servers/integrations/openai)_API_KEY is configured (default model gpt-4o-mini), the server sends the user's question to OpenAI's API to pick the right child server, tool, and arguments, then executes the call and returns the result with a routing explanation, trace steps, and citation sources.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
all-mcp — One MCP Server for All of Them
One MCP server containing all 60 of Mohammad Abbasi's MCP servers — Turkey (32), Germany (27), Bonbama (1) — 324 tools behind a single config entry. Ask anything; it connects to the right MCP itself.
Ask in Persian, Turkish, German, or English:
«قیمت بلیط قطار از برلین به مونیخ چقدره؟» → finds
flixtrain_search_trains, calls it, returns real departures and prices.
«قیمت اتوبوس مونیخ به هامبورگ» → routes to Germany transport, not Turkey — because the question names German cities.
How it actually works (honest version)
There is no magic detection inside this server. By default, your own AI — Claude Desktop, Claude Code, Cursor — does the detecting:
search_tools(query)— keyword search over all 324 tools in all four languages, ranked by topic match, place match (cities/countries named in the question), and your saved location. Returns the best tools with server, country, and a one-line description.call_tool(server, tool, arguments)— runs the chosen tool on the right child server (spawned on demand viauvx) and returns its real result.
Exposing all 324 tools at once would drown any client (context blowup, wrong picks). So the router exposes only 6 tools — the standard router pattern:
Tool | What it does |
| Ranked tools for a question (any language) |
| Run one tool on one child server |
| One-step answer: route + run + explain (see below) |
| Browse the 60 servers |
| Save your country for location-first routing (local file only) |
| Index counts, PyPI status, uvx, current location, routing provider |
One search + one call — no extra round trips. Or one ask — see next section.
Related MCP server: Router-MCP
ask: one-step answers (optional routing LLM)
ask(question) answers in a single call: it routes the question to the right server+tool+arguments, executes it, and returns the result plus a one-line routing explanation, alternatives, a routing trace (steps: one entry per routing/execution attempt, {server, tool, status, ms}), and citation links (sources).
Routing needs a small LLM. It uses your own key (or a local model) — the router never ships a key, and the key never leaves your machine except to the provider you chose:
Provider | Env var | Default model | Free? |
Gemini |
|
| Free tier at AI Studio |
OpenAI |
|
| Paid |
Anthropic |
|
| Paid |
OpenRouter |
|
| Free-tier models — good default with no paid key |
Ollama (local) | — |
| Fully free/local, no key at all |
Selection: LLM_PROVIDER env override (gemini / openai / anthropic / openrouter / ollama), else the first configured provider in that order. Ollama is only used when explicitly selected (LLM_PROVIDER=ollama, host http://localhost:11434 by default; ollama pull qwen2.5:7b first). Model overrides: ALL_MCP_<PROVIDER>_MODEL (e.g. ALL_MCP_GEMINI_MODEL).
No provider at all? ask still works: it falls back to the top search result — auto-executed when it needs no arguments, otherwise returned with the required parameters listed. search_tools + call_tool always work with no key at all.
HTTP bridge: the website chat UI
The site's chat talks to the router running on your own machine (local bridge — still no backend of ours):
uvx all-mcp --http --port 8765Localhost-only (127.0.0.1). Endpoints:
Endpoint | Body | Returns |
| — | servers/tools indexed, LLM configured yes/no (never the key) |
|
| ranked tools |
|
| the tool result |
|
| one-step answer + |
curl -X POST http://127.0.0.1:8765/api/ask \
-H 'Content-Type: application/json' \
-d '{"question": "قیمت بلیط قطار از برلین به مونیخ چقدره؟"}'CORS allows only https://mohammad-abbasi-sh.github.io and localhost origins. /api/ask accepts an optional per-request location hint ({"country": "DE", "city": "Berlin"}) sent by the chat UI from its browser memory — it beats the saved location, and explicit place names in the question still beat it. The response's steps array is the live routing trace the chat UI animates ("connecting to flixtrain-mcp…"), and sources are the citation links.
Install (one config entry)
Requires uvx (install uv). Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"all-mcp": {
"command": "uvx",
"args": ["all-mcp"],
"env": {
"USER_COUNTRY": "DE"
}
}
}
}USER_COUNTRY is optional (DE / TR / IR): it tells the router where you are, so an ambiguous question with no place names routes to your country's services. Set it once at install. Without it, use the set_location tool (saved to ~/.config/all-mcp/location.json on your machine only).
Then just ask questions. Try: «هوای برلین چطوره؟», «dollar exchange rate today», «Fußball Ergebnisse Bundesliga», «تخفیف گرگان».
Ranking priority
Explicit place names in the question win. «اتوبوس مونیخ به هامبورگ» routes to Germany even if your saved location is Turkey.
A per-request location hint beats the saved location. The chat UI sends
{"country", "city?"}from its browser memory with each/api/ask(or theasktool'slocationargument) — it wins overUSER_COUNTRY/set_location, but still loses to place names in the question.Saved location breaks ties. A bare «قیمت بلیط اتوبوس» with
USER_COUNTRY=DEranks German options first; withTR, Turkish ones.No cue, no location: both countries' options are returned ranked — your AI asks you which country you mean instead of guessing.
Every search result carries the server's country + one-line description, so the AI can itself disambiguate.
Privacy
Everything runs locally on your machine: stdio, no backend, no account, no telemetry. No API key is needed for search/call. Your location (env var, local file, or per-request hint) never leaves the machine. Child servers inherit your own session variables (see below) and nothing is ever logged, printed, or stored. The only network call the router itself makes is ask's routing call — and only when you configured a provider: your question goes to that provider (or stays on your machine with Ollama), and your key is sent only in the request header to that provider, never logged or stored.
Account actions (sessions)
Two servers have write tools that act inside your own account (cart, favorites): hepsiburada-mcp and migros-mcp. They use your own session cookie, passed as an env var in your MCP config — it never leaves your machine:
"env": {
"USER_COUNTRY": "DE",
"HEPSIBURADA_SESSION": "your-session-cookie",
"MIGROS_SESSION": "your-session-cookie"
}Write actions always need explicit confirm=true in the arguments — enforced by the child servers, forwarded unchanged by the router. Payment is never automated: order tools return a checkout link and stop.
Servers not on PyPI yet (6)
These servers are in the index but their packages are not published yet, so call_tool returns a clear error instead of hanging: paribu-mcp, diyanet-mcp, osym-mcp, heise-mcp, zeit-mcp, welt-mcp. They will work automatically once published (the index regenerates on every factory run).
The hierarchy
all-mcp (this repo) — the main reference: one entry point for everything.
Turkey MCP + Germany MCP — the catalogs and platforms (turkey-mcp, germany-mcp).
Individual MCP repos — one repo per service.
Every new server added by the daily factory runs updates this index too. The index is generated, never hand-written:
python3 gen_index.py # regenerate from the local catalogs
python3 gen_index.py --probe # also refresh real inputSchemas via uvxgen_index.py is cron-friendly: non-interactive, idempotent (exit 0, file untouched when nothing changed), atomic writes, and a short summary on stdout. Factory cron command:
python3 ~/workspace/github-profile/projects/all-mcp/gen_index.pyDevelopment
python -m pytest tests/ -q # offline suite (103 tests)
python tests/smoke_live.py # live smoke: 6 checks (needs network + uvx)License
PolyForm Noncommercial 1.0.0 — free for personal and non-commercial use. Commercial use needs a separate license: contact Mohammad Abbasi.
Built by Mohammad Abbasi — https://almanibama.ir · https://mabbasi.ir
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Geocoding, routing, isochrones, traffic, weather, and place search for AI agents. 19 MCP tools.
The Ferryhopper MCP server is a connector for LLMs and AI Agents in maritime travel that exposes ferry routes, schedules, and booking options. It enables AI assistants to search ports and connections across 33 countries and 190+ ferry operators, provide real-time ferry itineraries with indicative prices, and assist users with planning island-hopping or multi-leg journeys by processing natural language queries about ferry times, passenger counts, and travel durations.
Operator-as-agent MCP hub. 6 tools. First $5 free, then $0.001/call.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides a semantic search interface that enables discovery and routing across over 1,000 local MCP tools using natural language queries. It leverages hybrid search and embeddings to accurately match user intent with tool names and descriptions.6 npm1MIT
- FlicenseCqualityDmaintenanceRoutes natural language queries to appropriate MCP tools and planners with high-precision semantic matching and safety guardrails. Supports multi-intent detection, task planning, and strict role-based filtering to prevent misexecution or unauthorized access.7-
- AlicenseNot gradedqualityDmaintenanceMCP server that routes natural language requests to structured tool calls using a LoRA-tuned small language model, with built-in validation, retry, and fallback recovery.MIT
- FlicenseNot gradedqualityDmaintenanceCentralized MCP server that intelligently routes user queries to appropriate MCP tools, aggregates responses from multiple servers, and supports both rule-based and AI-powered routing.3-