Provides summarised output from various actions that could otherwise eat up tokens and cause crashes
MCP Summarization Functions MCP server exists for a simple reason — assistants are far more useful when they can act on MCP Summarization Functions directly instead of describing what you should do. Provides summarised output from various actions that could otherwise eat up tokens and cause crashes.
A powerful MCP server that provides intelligent summarization capabilities through a clean, extensible architecture. Built with modern TypeScript and designed for seamless integration with AI workflows.
Once MCP Summarization Functions is connected, these are the calls the assistant has available:
summarize_command — Execute and summarize command output. typescript { // Required command: string, // Command to execute cwd: string, // Working directory for commandsummarize_files — Summarize file contents. typescript { // Required paths: string[], // Array of file paths to summarize (relative to cwd) cwd: string, // Workingsummarize_directory — Get directory structure overview. typescript { // Required path: string, // Directory path to summarize (relative to cwd) cwd: string, // Workingsummarize_text — Summarize arbitrary text content. typescript { // Required content: string, // Text content to summarize type: string, // Type of content (e.g., "logget_full_content — Retrieve the full content for a given summary ID. typescript { // Required id: string // ID of the stored content }The server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
You will need 6 environment variables: PROVIDER, API_KEY, MODEL_ID, MCP_WORKING_DIR, PROVIDER_BASE_URL, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the file and storage access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Summarization Functions's toolset — summarize_command, summarize_files, summarize_directory and 2 more — is a fair guide to whether it matches your workflow. It is maintained by Braffolk; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against MCP Summarization Functions's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| summarize_command | Execute and summarize command output. typescript { // Required command: string, // Command to execute cwd: string, // Working directory for command execution |
| summarize_files | Summarize file contents. typescript { // Required paths: string[], // Array of file paths to summarize (relative to cwd) cwd: string, // Working directory for resolving file paths |
| summarize_directory | Get directory structure overview. typescript { // Required path: string, // Directory path to summarize (relative to cwd) cwd: string, // Working directory for resolving directory path |
| summarize_text | Summarize arbitrary text content. typescript { // Required content: string, // Text content to summarize type: string, // Type of content (e.g., "log output", "API response") |
| get_full_content | Retrieve the full content for a given summary ID. typescript { // Required id: string // ID of the stored content } |
{
"mcpServers": {
"summarization-functions": {
"command": "npx",
"args": ["-y", "@smithery/cli"],
"env": {
"PROVIDER": "your-value",
"API_KEY": "your-value",
"MODEL_ID": "your-value",
"MCP_WORKING_DIR": "your-value",
"PROVIDER_BASE_URL": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| PROVIDER | Configuration value read at startup. | Optional |
| API_KEY | Credential the server authenticates with. | Yes |
| MODEL_ID | Configuration value read at startup. | Optional |
| MCP_WORKING_DIR | Filesystem location the server is allowed to use. | Optional |
| PROVIDER_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Model Context Protocol (MCP) tool to interact with Claude Desktop on macOS
Upload, search, transform and organise your Cloudinary media library from a chat window