ai-workers-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Your Gemini API key (used as fallback if no config file exists) |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ai_summarizeA | Summarize a URL or plain text using a configured free LLM. Pass url OR text (not both). Plain text only — no code or secrets. |
| ai_translateA | Translate plain text to a target language using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_generateA | Generate text from a prompt using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_rewriteB | Rewrite plain text in a given style using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_proofreadA | Proofread plain text and list corrections using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_bulletA | Extract key points from plain text as a markdown bullet list using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_outlineA | Create a hierarchical markdown outline from plain text using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_classifyA | Classify plain text into one of the provided labels using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_extractA | Extract named fields from plain text as JSON using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_qaA | Answer a question about a URL or plain text using a configured free LLM. Pass url OR text (not both). Plain text only — no code or secrets. |
| ai_compareB | Compare two plain texts and highlight similarities and differences using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
| ai_email_draftA | Draft an email body from bullet points using a configured free LLM. Plain prose only — no code, secrets, or file paths. |
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 12 tools
Each tool has a clearly distinct purpose: bullet points, classification, comparison, email drafting, field extraction, free generation, outlining, proofreading, Q&A, rewriting, summarization, and translation. Overlap is minimal and descriptions effectively disambiguate.
All tools follow an ai_verb pattern (e.g., ai_bullet, ai_classify). The outlier is ai_email_draft, which uses a noun+verb combination, but the pattern is otherwise consistent.
With 12 tools, the set is well-scoped for a general-purpose LLM text processing server. It covers a broad range of common tasks without being overwhelming.
The tools cover most common text operations (generate, summarize, classify, translate, etc.). Minor gaps exist (e.g., sentiment analysis, grammar checking), but the core functionality is solid.