Context Optimizer MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONTEXT_OPT_EXA_KEY | No | Your Exa.ai API key for research tools | |
| CONTEXT_OPT_CLAUDE_KEY | No | Your Claude (Anthropic) API key | |
| CONTEXT_OPT_GEMINI_KEY | No | Your Google Gemini API key | |
| CONTEXT_OPT_OPENAI_KEY | No | Your OpenAI API key | |
| CONTEXT_OPT_LLM_PROVIDER | No | The LLM provider to use (e.g., 'gemini', 'claude', 'openai') | |
| CONTEXT_OPT_ALLOWED_PATHS | No | Allowed file paths for security validation |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| askAboutFileA | Extract specific information from files without reading their entire contents into chat context. Works with text files, code files, images, PDFs, and more. |
| runAndExtractB | Execute terminal commands and intelligently extract specific information from their output. Supports cross-platform command execution with security controls. |
| askFollowUpA | Ask follow-up questions about the previous terminal command execution without re-running the command. Only available after using runAndExtract tool. |
| researchTopicB | Conduct quick, focused web research on software development topics using Exa.ai's powerful research capabilities for current information and practical implementation guidance. |
| deepResearchB | Conduct comprehensive, in-depth research using Exa.ai's exhaustive analysis capabilities for critical decision-making and complex architectural planning. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct source and action: file analysis, quick web research, deep web research, terminal command follow-up, and terminal execution with extraction. While researchTopic and deepResearch are related, their descriptions clearly separate quick versus exhaustive research, preventing mis-selection.
Names are readable and mostly camelCase, but follow different patterns: askAboutFile and askFollowUp use 'ask' + phrase, researchTopic is verb+noun, deepResearch is an adjective-noun phrase, and runAndExtract is verb+verb. The mixed conventions are still predictable in context but lack a consistent verb_noun structure.
Five tools is well-scoped for a context optimization server. Each tool fills a clear niche—file extraction, quick research, deep research, command execution extraction, and follow-up—without redundancy or clutter.
The surface covers the main context-gathering needs: files, web research, and terminal output. A minor gap is that askFollowUp only attaches to runAndExtract, leaving no follow-up mechanism for askAboutFile or research results, but agents can still work around this.