math-anchor
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MATH_ANCHOR_PYTHON | No | Optional. Set only when selecting a specific Python interpreter (Python 3.11 or newer). | |
| MATH_ANCHOR_SDKROOT | No | Optional. Explicit override for the SDK root used by Swift scripts. |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| math.runA | Use for exact or reliability-sensitive mathematics, especially fixed-width overflow and bits, IEEE-754, named rounding or division conventions, large integers, matrices, units and dimensions, uncertainty, probability, numerical methods, or finance. Do not use for trivial low-risk arithmetic. Always pass operation-specific fields inside the arguments object: {operation, arguments}; never flatten them. Known direct shapes need no describe call: integer.machine_arithmetic arguments include action, left, right, bitWidth, signedness, inputMode, and overflowBehavior; combinatorics.count arguments use action, n, and k. The typed operation keeps exact and approximate results separate; one successful ordinary call is sufficient. |
| math.batchA | Run 1 to 32 independent operations in order with per-item limits. |
| math.searchA | Search operations only when the id is unknown; otherwise use math.run. |
| math.describeA | Get schema and argument examples only for one unfamiliar operation selected by math.search. Do not call this for known integer.machine_arithmetic or combinatorics.count shapes. Examples are arguments objects; nest one under math.run.arguments and pass its id as math.run.operation. |
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
Each tool has a clearly distinct role: run executes a single operation, search finds operation IDs, describe returns schemas, and batch executes multiple operations. There is no meaningful overlap between them.
All tool names follow the same math.<verb> convention with lowercase identifiers. The names are short, predictable, and consistent with each other.
Four tools is well-scoped for this server: a single execution tool covering many operations, plus search, describe, and batching support. Each tool earns its place without redundancy.
The surface covers the full workflow of discovering an operation, understanding its schema, executing it, and batching multiple operations. Since math operations are stateless, no update or delete lifecycle is needed.