Estimate token usage for tool definitions in the agent context window to decide on progressive loading.
MIT
459,732 tools. Updated 2026-08-17 08:46
"How to increase a model's context window for handling large files" matching MCP tools:
- Export full SINIM municipal panels to Parquet or CSV files, bypassing model context limits for extensive queries.MIT
- Send a file path and a question to analyze a file server-side. The file never enters your context window; returns analysis with metadata and token usage.MIT
- Upload local files to Databricks Unity Catalog volumes for data processing. Supports large files with progress tracking and error handling.MIT
- Retrieve the complete content of any Google Drive file for full analysis or transformation. Use only when you need the entire file, as it can be large.MIT
- Filter large local text files by relevance to a query, returning verbatim line-numbered spans to keep context small.MIT
Matching MCP Servers
- Alicense-qualityCmaintenanceA minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers.MIT
- AlicenseAqualityCmaintenanceEnables downloading real binary files from Egnyte and uploading large files with chunked support, complementing the official Egnyte MCP connector.5Apache 2.0
Matching MCP Connectors
Read-only Increase banking observability plus one safe non-money-moving write, for AI agents.
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
- Export SQL query results directly to CSV or JSONL files, handling large datasets without loading into context.MIT
- View the complete diff for a single file without truncation to review all changes in large files like lock files or generated code before staging.MIT
- Replace or insert text at specific line ranges in files using line-number operations. Ideal for large files or precise edits without context-heavy processing.MIT
- Read file contents from the filesystem, handling large files through chunked reading with line-based pagination for efficient processing.MIT
- Access a specific Pine Script v6 documentation file using its path. Use limit and offset to manage token usage for large files.MIT
- Assess repository health with a compact score and top-5 hotspot files from a scan, fitting in one LLM context window, to decide if full pagination is needed.MIT
- Analyze error handling patterns in your codebase to uncover inconsistencies, missing error handling, and evolution over time, with actionable recommendations for consistency.Apache 2.0
- Inspect a memory node's evidence, validity window, and connected context to audit why it exists or how it changed.Apache 2.0
- Load multiple files, compress them into temporary libraries, and retrieve context for any query to understand large codebases without permanent storage.MIT
- Measures token-window context fullness and tracks tokens saved by optimization. Alerts when to save a handoff and clear the session to maintain optimal context usage.MIT
- Calculate the maximum legal rent increase in Dubai by comparing your current rent to the RERA Rent Index. Get the gap, increase percentage, and new rent.MIT
- Check how much of your context window is consumed before a conversation starts, broken down by skills, memory files, and MCP servers.MIT
- Reads specific directories or files and returns a distilled architectural index, allowing you to understand a codebase subset without processing all raw content.MIT
- Converts PDF, DOCX, XLSX, and CSV files into compact markdown before they enter the context window, reducing token usage by up to 98%.MIT