verdoc-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VERDOC_ORIGIN | No | Override the endpoint URL (for testing). | https://verdoc.dev |
| EVM_PRIVATE_KEY | No | Wallet private key that pays for requests. Omit to run in quote-only mode. | |
| VERDOC_MAX_SPEND_USD | No | Hard per-call spending ceiling in USD. Nothing above it is ever signed. | 0.05 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| verdoc_agents_mdA | Generate an AGENTS.md for a public GitHub repository: build and test commands quoted from the repository's own manifests with the source file named, a directory map, entry points and edit boundaries. Every path is checked against the git tree and anything ambiguous is marked unverified rather than guessed. Use this before working in a repository you do not already know. Costs $0.02 in USDC from the configured wallet. |
| verdoc_scanA | Structured facts about a public GitHub repository: toolchain commands with the manifest each was quoted from, directory layout, language split, CI and test presence, a 0-100 documentation-health score, and phantom_paths - paths the README cites that do not exist in the git tree. Deterministic; no language model. Costs $0.01 in USDC. |
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
The two tools have distinct outputs: one generates an AGENTS.md file, the other returns structured facts and a score. There is some overlap in the underlying data (toolchain, directory layout), but the purpose and return type are clear enough to avoid serious confusion.
Both tools share the 'verdoc_' prefix, but the suffixes are inconsistent: 'agents_md' is a noun-phrase while 'scan' is a verb. They are readable and predictable, but not a strict verb_noun pattern.
With only two tools, the server feels thin, but it is scoped to a narrow domain (analyzing GitHub repos). The small count is not unreasonable, though it leaves room for more related tools.
The domain is repository analysis, and the two tools cover the core operations: generating an AGENTS.md guide and performing a detailed scan. Minor gaps exist (e.g., no direct metadata-only fetch), but for the stated purpose the surface is reasonably complete.