Vellum
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| count_textA | Count characters, words, lines, sentences and bytes in a piece of text, exactly. Use this whenever the answer needs to be a precise number, because reading tokens is not the same as counting characters. Reports visible characters separately from code points, which differ for accents and emoji. |
| score_readabilityA | Score how hard a piece of text is to read, using Flesch reading ease and a grade level, with a plain description of what the number means. Also reports the longest sentence, which is usually the reason prose scores badly. |
| diff_textsA | Compare two versions of a text and return a unified diff plus exact counts of lines added and removed and a similarity percentage. Use it rather than reading both versions and describing the difference. |
| test_regexA | Run a regular expression against text and report every match with its position and capture groups. An invalid pattern comes back as an error message rather than an exception. Use it to check a pattern actually does what it looks like it does. |
| hash_textA | Compute a cryptographic hash of some text. Deterministic, and not something that can be worked out by reading. |
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 5 tools
Each tool performs a unique, clearly distinguishable operation: counting metrics, readability assessment, diffing, regex testing, and hashing. There is no overlap or ambiguity between them, so an agent can reliably pick the right tool for a given task.
All tool names follow a consistent verb_noun pattern (count_text, score_readability, diff_texts, test_regex, hash_text) using snake_case throughout. The naming is predictable and immediately conveys the action and object.
With exactly five tools, the server is well-scoped for a text utility purpose. Each tool covers a distinct need without bloat, and the count is within the ideal range for clarity and usability.
The set covers core text analysis and manipulation operations (counting, readability, diffing, regex, hashing). Minor gaps like string transformation or encoding conversion exist, but these are not obvious dead-ends for the primary use cases, so the surface is reasonably complete.