CG Alpha MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ELFA_BASE | No | ELFA base URL (defaults to https://api.elfa.ai) | https://api.elfa.ai |
| ELFA_HEADER | No | Header name for auth (defaults to x-elfa-api-key) | x-elfa-api-key |
| ELFA_API_KEY | Yes | API key required for ELFA calls. Get from ELFA (https://www.elfa.ai/api). | |
| ELFA_AUTH_TYPE | No | Set to x-elfa-api-key (default) or bearer | x-elfa-api-key |
| COINGECKO_API_KEY | No | Optional API key for CoinGecko if you use the CoinGecko MCP with a key |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| elfa_set_authA | Set ELFA API auth. Params: key (string), headerName (Authorization|x-elfa-api-key), scheme (e.g., Bearer). |
| elfa_set_baseB | Set ELFA base URL (e.g., https://api.elfa.ai). |
| elfa_reload_envB | Reload .env files from common locations. |
| elfa_statusB | Show current ELFA config (key masked) and .env load info. |
| elfa_queryB | Generic ELFA proxy. Call any ELFA path with method/query/body. Returns JSON. |
| elfa_trendingC | Alias to /v2/aggregations/trending-tokens (timeframe, chain, limit, cursor). |
| elfa_trending_tokensC | Trending tokens aggregation. Params: timeframe, chain, limit, cursor. |
| elfa_token_newsC | Token news. Params: symbols (comma), chain, start, end, limit, cursor, sources. |
| elfa_keyword_mentionsB | Multi-keyword mentions. Params: keywords (array|string), start, end, chain, limit, cursor, sources. |
| ta_rsiA | Compute RSI (Wilder). Inputs: values:number[] (oldest→newest), period?:number(14). Returns latest RSI. |
| ta_bollingerB | Compute Bollinger Bands (SMA + population stdev). Inputs: values:number[] (oldest→newest), period?:number(20), mult?:number(2). |
| ta_summaryB | Return both RSI and Bollinger in one call. Inputs: values:number[] (oldest→newest), rsiPeriod?:number(14), bbPeriod?:number(20), bbMult?:number(2). |
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
Most tools have distinct purposes, but there is some overlap: 'elfa_trending' and 'elfa_trending_tokens' appear to serve similar functions, with the former being an alias. The ELFA configuration tools (set_auth, set_base, reload_env, status) are clearly distinct from query and analysis tools, and the technical analysis tools (bollinger, rsi, summary) are well-differentiated, though 'ta_summary' combines functionality from the other two.
Naming is mostly consistent with a clear prefix pattern: 'elfa_' for ELFA-related tools and 'ta_' for technical analysis tools. However, there are minor deviations: 'elfa_trending' is an alias that doesn't follow the verb_noun pattern as strictly as others, and 'elfa_query' uses a generic term that could be more descriptive. Overall, the conventions are readable and predictable.
With 12 tools, the count is well-scoped for the server's purpose, which combines ELFA API interactions and technical analysis. Each tool earns its place, covering configuration, data retrieval, and analysis without being overly broad or sparse. This number allows for comprehensive functionality while remaining manageable.
The tool surface is largely complete for its domain, covering ELFA API configuration, data querying (keyword mentions, token news, trending tokens), and technical analysis (RSI, Bollinger Bands). A minor gap is the lack of tools for more advanced ELFA operations beyond basic queries, but core workflows are well-supported, and agents can work around this with the generic 'elfa_query' tool.