mcpField
M
Mcp_tool_chainer

Mcp_tool_chainer

Local
github.com/thirdstrandstudioAI & Agents57Updated 64w ago

About Mcp_tool_chainer

MCP Tool Chainer is an MCP server that runs several MCP tool calls in sequence, passing each result to the next step. It targets users who want to combine tools while reducing LLM round-trips and token use, and it supports JsonPath filtering of inputs and outputs.

Key features

  1. 01Chains multiple MCP tool calls in sequence
  2. 02Passes prior results with a CHAIN_RESULT placeholder
  3. 03Applies JsonPath to inputs and outputs
  4. 04Discovers tools automatically from configured servers

Use cases

  1. 01Feeding fetched web content directly into an XPath tool
  2. 02Extracting part of a tool's output before the next step
  3. 03Combining several tools into one data processing call

MCP support

MCP Tool Chainer is an MCP server that exposes mcp_chain, chainable_tools and discover_tools, and it connects to other configured MCP servers to discover and call their tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"tool-chainer": {
"command": "npx",
"args": [
"-y",
"@thirdstrandstudio/mcp-tool-chainer"
]
}
}
}
Run commandnpx -y @thirdstrandstudio/mcp-tool-chainer

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@thirdstrandstudio/mcp-tool-chainer

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Tool Chainer

Visit Third Strand Studio

An MCP (Model Context Protocol) server that chains calls to other MCP tools, reducing token usage by allowing sequential tool execution with result passing. Designed to solve https://github.com/modelcontextprotocol/specification/issues/215

image

Step function like JSON paths:

image

Features

  • Chain multiple MCP tools together in sequence
  • Pass results from one tool as input to another tool using CHAIN_RESULT placeholder
  • Filter and extract specific data using JsonPath with inputPath and outputPath parameters
  • Automatic tool discovery from configured MCP servers
  • Minimal token usage compared to individual tool calls

Tools

This server implements the following MCP tools:

  1. mcp_chain - Chain together multiple MCP servers
  2. chainable_tools - Discover tools from all MCP servers so the mcp_chain tool can be used
  3. discover_tools - Rediscover tools from all MCP servers

Installation

Prerequisites
  • Node.js (v16 or later)
  • npm
Installing from npm
# Install
npm install @thirdstrandstudio/mcp-tool-chainer

# Or use with npx directly
npx -y @thirdstrandstudio/mcp-tool-chainer
Installing from source
# Clone the repository
git clone https://github.com/thirdstrandstudio/mcp-tool-chainer.git
cd mcp-tool-chainer

# Install dependencies
npm install

# Build the package
npm run build

Usage with Claude Desktop, Cursor etc

ENSURE IT IS THE LAST MCP TO RUN OTHERWISE IT WILL HAVE TO RUN DISCOVERY AGAIN

Add the following to your claude_desktop_config.json or mcp.json:

If installed from npm globally
{
  "mcpServers": {
    "mcp_tool_chainer": {
      "command": "npx",
      "args": ["-y", "@thirdstrandstudio/mcp-tool-chainer", "`claude_desktop_config.json` or `mcp.json`"],
      "env": {}
    }
  }
}
If installed from source
{
  "mcpServers": {
    "mcp_tool_chainer": {
      "command": "node",
      "args": ["/path/to/mcp-tool-chainer/dist/index.js", "`claude_desktop_config.json` or `mcp.json`"],
      "env": {}
    }
  }
}

Replace /path/to/mcp-tool-chainer with the actual path to your repository.

image

Examples

Chain Browser and XPath Tools
// Fetch a webpage and then extract specific content with XPath
const result = await callTool("mcp_chain", { 
  "mcpPath": [
    {
      "toolName": "mcp_browser_mcp_fetch_url",
      "toolArgs": "{\"url\": \"https://example.com\"}"
    },
    {
      "toolName": "mcp_xpath_xpath",
      "toolArgs": "{\"xml\": CHAIN_RESULT, \"query\": \"//h1\"}"
    }
  ]
});
Using JsonPath with InputPath and OutputPath
// Fetch a webpage, extract specific content with XPath, then extract part of the result
const result = await callTool("mcp_chain", { 
  "mcpPath": [
    {
      "toolName": "mcp_fetch_fetch",
      "toolArgs": "{\"url\": \"https://api.example.com/data\"}"
    },
    {
      "toolName": "web_search",
      "toolArgs": "{\"search_term\": CHAIN_RESULT}",
      "inputPath": "$.results[0].title",     // Extract only the first result's title from previous output
      "outputPath": "$.snippets[*].text"     // Extract only the text snippets from the search results
    },
    {
      "toolName": "another_tool",
      "toolArgs": "{\"content\": CHAIN_RESULT}"
    }
  ]
});

JsonPath Support

MCP Tool Chainer now supports AWS Step Functions-style InputPath and OutputPath features:

  • inputPath: JsonPath expression to extract specific portions of the input before passing to a tool
  • outputPath: JsonPath expression to extract specific portions of the output before passing to the next tool

These features work only when the input/output is valid JSON. If JsonPath extraction fails, the original input/output is used.

For JsonPath syntax reference, see JsonPath Syntax.

Benefits

  • Reduced Token Usage: By chaining tools together, you avoid sending large intermediate results back to the LLM
  • Simplified Workflows: Create complex data processing pipelines with a single tool call
  • Improved Performance: Reduce latency by minimizing round-trips between the LLM and tools
  • Precise Data Flow Control: Extract only the data you need with JsonPath expressions

Development

# Install dependencies
npm install

# Start the server
node dist/index.js config.json

# List available tools
node dist/index.js config.json discover_tools

License

This MCP server is licensed under the MIT License.


Created by Third Strand Studio

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.