Holded API MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOLDED_API_KEY | Yes | Your Holded API key. Create an API key in Holded → Settings → Developers. The server sends it as a Bearer token on every request. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| holded_search_operationsB | Search the offline API catalog by words, Holded api, or tag. Returns paginated summaries. |
| holded_get_operationB | Inspect an operation's description, required path/query parameters, and body schema. |
| holded_readC | Execute a catalog GET operation. Inspect its schema first. Returns {status, data}. |
| holded_writeA | Execute a catalog POST/PUT/PATCH/DELETE operation with user authorization. |
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 4 tools
The four tools have clearly distinct roles: search the catalog, inspect an operation schema, execute GET operations, and execute mutating operations. There is little risk of confusing read and write execution because the descriptions explicitly separate GET from POST/PUT/PATCH/DELETE.
All tools share the holded_ prefix and use readable verb/object-style names. The set is mostly consistent, though search_operations, get_operation, read, and write use slightly different granularity conventions.
Four tools are well-scoped for a catalog-backed API gateway: discovery, schema inspection, read execution, and write execution. Each tool has a clear purpose and no obvious redundant surface.
The catalog-search plus schema-inspection plus execute-read/write pattern can cover the full Holded API surface generically. Minor gaps may exist around authentication/setup guidance or catalog browsing beyond search, but the core lifecycle is present.