@zeromodern/mcp-server-0mod
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZERO_API_KEY | Yes | Your API key for the 0mod API Gateway. |
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 |
|---|---|
| stealth_domA | Fetch web pages from Cloudflare edge bypassing simple IP blocks |
| airgap_scrubB | Redact SSN, phone, email, and ZIP codes using Workers AI |
| rag_shrinkA | Compress raw HTML to clean markdown & headings for RAG context windows |
| code_denoiseB | Strip comments, docstrings, whitespace, and sourcemaps from code files |
| domain_checkA | Query global RDAP registry from edge for domain availability and WHOIS status |
| dex_price_summaryA | Fetch real-time DEX price, 24h volume, liquidity, and top pair stats across chains |
| x_sentimentB | Analyze market & social sentiment for topics/tokens using Workers AI Llama 3.1 |
| image_ocr_shrinkA | Extract clean text and table markdown from images via Workers AI Vision Llama 3.2 |
| embed_textC | Generates 768-dimensional dense vector embeddings for RAG & semantic search via BAAI BGE-Base |
| embed_multilingualA | Generates 1024-dimensional dense vector embeddings for multilingual & long text via BAAI BGE-Large |
| summarize_textC | Executive TL;DR text summarizer producing structured bullet points via Workers AI Llama 3.1 |
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 11 tools
Most tools target distinct tasks (scraping, redaction, compression, sentiment, embeddings), and descriptions clarify their purposes. The only near-overlap is between embed_text and embed_multilingual, but their language/vector-size differences make them distinguishable.
Tool names mix verb-noun patterns (embed_text, summarize_text), noun-compounds (dex_price_summary, x_sentiment), and adjective-noun/cryptic forms (stealth_dom, rag_shrink, airgap_scrub). No consistent naming convention is used across the set.
With 11 tools, the count is within a reasonable range and not excessive. However, the tools span diverse domains (web/data, cleaning, AI analysis), giving the set a somewhat scattershot feel rather than a focused toolkit.
There is no clear domain or lifecycle model; the tools are a random assortment of utilities. Obvious operations are missing (e.g., search, translation, storage) that would make workflows coherent, and the breadth of unrelated features prevents a sense of complete coverage.