code-mode-alchemy-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ALCHEMY_API_KEY | Yes | Your Alchemy API key | |
| ALCHEMY_NETWORK | Yes | The target blockchain network (e.g., eth-mainnet) |
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 |
|---|---|
| searchA | Search Alchemy's API endpoints by keyword. Returns matching endpoints with their paths, methods, parameters, and server URLs. Use this before execute() to discover the right endpoint. |
| executeA | Execute JavaScript code against Alchemy's APIs. The sandbox provides:
REST example: JSON-RPC example: |
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 2 tools
Search and execute have clearly distinct roles: search discovers API endpoints, while execute runs arbitrary JavaScript against them. There is no overlap in purpose, and the descriptions explicitly guide sequential use.
Both tool names are concise, lowercase imperative verbs following the same bare-verb convention. No inconsistent casing or mixed noun/verb patterns.
Two tools is slightly below the typical 3-15 range, but both are essential and earn their place: one for discovery and one for universal execution. The set is minimal rather than redundant.
Search plus execute covers endpoint discovery and arbitrary REST/JSON-RPC calls, which is nearly complete for a code-mode API gateway. Minor gaps remain, such as no structured endpoint-schema lookup or built-in pagination helpers, but agents can work around these.