Allows running Deno scripts with network and environment permissions, including fetching data from APIs and executing TypeScript code

Enables execution of Git commands through shell scripts, with examples showing git status checks and branch operations

Enables AI agent functionality with web search using Gemini 2.5 Flash model through Google's GenAI API for information retrieval and analysis

Supports executing Node.js scripts for data processing and computation tasks with access to input parameters in JSON format

Allows execution of npm commands for building projects and running tests through shell scripts

Provides AI agent capabilities with web search using GPT-5 model through the OpenAI API for answering queries and research tasks

Enables running Python scripts for data analysis and processing tasks with access to environment variables and JSON output

1. Click on "Install Server".

2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.

3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@any-script-mcp run git_status with verbose mode on"

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.

$ claude mcp add any-script \
 -s user \
 -- npx any-script-mcp

{
 "mcpServers": {
 "any-script": {
 "command": "npx",
 "args": ["any-script-mcp"]
 }
 }
}

# Single configuration file
$ ANY_SCRIPT_MCP_CONFIG=/path/to/custom/config.yaml npx any-script-mcp

# Multiple configuration files (Unix/macOS - separated by colon)
$ ANY_SCRIPT_MCP_CONFIG=/path/to/custom.yaml:$XDG_CONFIG_HOME/any-script-mcp/config.yaml npx any-script-mcp

# Multiple configuration files (Windows - separated by semicolon)
$ ANY_SCRIPT_MCP_CONFIG=C:\path\to\custom.yaml;%APPDATA%\any-script-mcp\config.yaml npx any-script-mcp

$ npx @modelcontextprotocol/inspector npx any-script-mcp

# yaml-language-server: $schema=https://raw.githubusercontent.com/izumin5210/any-script-mcp/main/config.schema.json
tools:
 - name: echo
 description: Echo a message
 inputs:
 message:
 type: string
 description: Message to echo
 run: |
 echo "Received: $INPUTS__MESSAGE"
 
 - name: git_status
 description: Check git status with optional branch
 inputs:
 branch-name:
 type: string
 description: Branch to check out
 required: false
 verbose:
 type: boolean
 description: Show verbose output
 default: false
 run: |
 if [ -n "${INPUTS__BRANCH_NAME:-}" ]; then
 git checkout "$INPUTS__BRANCH_NAME"
 fi
 
 if [ "$INPUTS__VERBOSE" = "true" ]; then
 git status -v
 else
 git status
 fi
 
 # Delegate search to codex CLI. Inspired by https://github.com/yoshiko-pg/o3-search-mcp
 - name: codex-search
 description: AI agent with web search for researching latest information, troubleshooting program errors, discussing complex problems and design decisions, exploring advanced library usage, and investigating upgrade paths. Supports natural language queries.
 inputs:
 prompt:
 type: string
 description: What you want to search, analyze, or discuss with the AI agent
 run: |
 codex exec \
 --model gpt-5 \
 --sandbox workspace-write \
 --config "sandbox_workspace_write.network_access=true" \
 "$INPUTS__PROMPT" \
 --json \
 | jq -sr 'map(select(.msg.type == "agent_message") | .msg.message) | last'
 timeout: 600000 # 10 minutes for complex AI operations
 
 - name: build
 description: Run build process with tests
 run: |
 npm run build
 npm test
 timeout: 180000 # 3 minutes for build and test

// Node.js
const inputs = JSON.parse(process.env.INPUTS_JSON);
console.log(inputs.num * 2); // count is a number, not a string

# yaml-language-server: $schema=https://raw.githubusercontent.com/izumin5210/any-script-mcp/main/config.schema.json
tools:
 # Python script
 - name: python_analysis
 description: Analyze data with Python
 shell: "python {0}"
 inputs:
 data:
 type: string
 description: Data to analyze
 run: |
 import os
 import json
 
 data = os.environ['INPUTS__DATA']
 # Process data with Python
 result = {"analysis": f"Processed: {data}"}
 print(json.dumps(result))

 # Deno script
 - name: deno_fetch
 description: Fetch data with Deno
 shell: "deno run --allow-net {0}"
 inputs:
 endpoint:
 type: string
 description: API endpoint
 run: |
 const endpoint = Deno.env.get("INPUTS__ENDPOINT");
 const response = await fetch(endpoint);
 console.log(await response.json());
 
 # Using INPUTS_JSON for type preservation
 - name: add_2
 description: add 2 to a number
 shell: "node {0}"
 inputs:
 num:
 type: number
 description: a number to add 2 to
 run: |
 const inputs = JSON.parse(process.env.INPUTS_JSON);
 console.log(inputs.num + 2); // number is a number, not a string

# yaml-language-server: $schema=https://raw.githubusercontent.com/izumin5210/any-script-mcp/main/config.schema.json
tools:
 - name: gemini-search
 description: AI agent with web search using Gemini 2.5 Flash
 shell: "deno run -N -E {0}"
 inputs:
 query:
 type: string
 description: Query for AI search
 required: true
 run: |
 import { GoogleGenAI } from "npm:@google/genai@^1";
 const inputs = JSON.parse(Deno.env.get("INPUTS_JSON"));
 const ai = new GoogleGenAI({ apiKey: Deno.env.get("GEMINI_API_KEY") });
 const res = await ai.models.generateContent({
 model: "gemini-2.5-flash",
 contents: inputs.query,
 config: {
 tools: [{ googleSearch: {} }],
 systemInstruction: "...",
 },
 });
 console.log(
 res.candidates?.[0]?.content?.parts?.map((p) => p.text ?? "").join(""),
 );

 - name: gpt-5-search
 description: AI agent with web search using GPT-5
 shell: "deno run -N -E {0}"
 inputs:
 query:
 type: string
 description: Query for AI search
 required: true
 run: |
 import OpenAI from "jsr:@openai/openai";
 const inputs = JSON.parse(Deno.env.get("INPUTS_JSON"));
 const client = new OpenAI({ apiKey: Deno.env.get("OPENAI_API_KEY") });
 const res = await client.responses.create({
 model: "gpt-5",
 tools: [{ type: "web_search_preview" }],
 input: inputs.query,
 instructions: "...",
 });
 console.log(res.output_text);

Looking for Admin?