agent-utils-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| X402_NETWORK | No | Payment network | base |
| X402_RPC_URL | No | Base JSON-RPC endpoint | https://mainnet.base.org |
| X402_CHAIN_ID | No | Payment network chain ID | 8453 |
| RATE_LIMIT_FREE | No | Free requests per IP per 24h | 100 |
| X402_USDC_CONTRACT | No | Payment network USDC contract | Base USDC |
| X402_PRICE_MICROUSD | No | Price per request in USDC atomic units | 1000 |
| X402_WALLET_ADDRESS | No | Wallet that receives payments | |
| X402_MAX_TIMEOUT_SECONDS | No | Payment validity window | 60 |
| X402_SETTLER_PRIVATE_KEY | No | Key that submits settlement transactions | |
| X402_SETTLE_MIN_MICROUSD | No | Batch payments until pending value reaches this | 0 |
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 |
|---|---|
| tool_json_validateA | Validate a JSON string. Returns parsed object or detailed error. |
| tool_json_formatB | Pretty-print or minify a JSON string. |
| tool_base64_encodeA | Encode a string to base64. |
| tool_base64_decodeA | Decode a base64 string. |
| tool_hash_generateA | Generate hash (md5, sha256, sha512) of input text. |
| tool_uuid_generateA | Generate a UUID (v4 or v7). |
| tool_url_parseB | Parse a URL into components (scheme, host, path, params, etc.). |
| tool_regex_testB | Test a regex pattern against text and return all matches. |
| tool_markdown_to_htmlC | Convert Markdown to HTML. |
| tool_html_to_markdownA | Convert HTML to Markdown. |
| tool_text_statsA | Compute text statistics: word count, char count, sentences, reading time. |
| tool_slug_generateB | Generate a URL-safe slug from text. |
| tool_datetime_convertC | Convert a datetime between timezones/formats, including Unix timestamps. |
| tool_cron_parseA | Parse a cron expression: human-readable description + next N run times. |
| tool_diff_textA | Compute a unified diff between two texts. |
| tool_csv_to_jsonB | Convert CSV text to a JSON array of objects. |
| tool_json_to_csvB | Convert a JSON array to CSV text. |
| tool_jwt_decodeA | Decode a JWT payload without verification (inspection only). |
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 18 tools
Each tool performs a distinct operation, with clear separation between encoding/decoding, validation/formatting, conversion pairs, and parsing utilities. No overlapping responsibilities would confuse an agent.
Names follow a consistent lowercase snake_case pattern with a uniform 'tool_' prefix and typically include the target data type, but verb placement varies (e.g., tool_text_stats vs tool_json_validate) and conversion pairs use 'to' rather than a strict verb_noun scheme.
18 tools is slightly above the typical well-scoped range, but the broad utility-toolkit purpose justifies the number since each tool addresses a distinct text, data, or time operation.
The set covers a wide range of common agent utilities (JSON, base64, hashing, UUID, datetime, CSV, Markdown, diff). Minor gaps such as URL encoding/decoding or more advanced string operations are missing, but the surface is generally complete for its stated purpose.