Understand-Anything MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UA_LICENSE_KEY | No | License key for Pro features (optional for free tier) | |
| UA_PROJECT_PATH | Yes | Path to the project to scan |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ua_status | Check the operational status of the Understand-Anything MCP server. Call this to verify if the knowledge graph is successfully loaded and active. |
| ua_scan | Check if a knowledge graph file is present and currently loaded. Returns instructions on how to generate the graph if missing. |
| ua_graph_summaryA | Get a high-level statistical summary of the codebase knowledge graph. Returns total node and edge counts to gauge project size. |
| ua_architecture_reportA | Generate a module-level architecture report from the knowledge graph. Returns a breakdown of files per directory to identify main components. |
| ua_dependency_report | Generate a top-level dependency report from the knowledge graph. Identifies the most heavily depended-on files in the codebase (high fan-in). |
| ua_explain | Explain a specific part of the codebase by retrieving its 1-hop dependencies. Call this to understand what a file imports and where it is used. |
| ua_onboarding_doc | Generate an onboarding overview document for new developers. Call this first when entering a new codebase to get oriented. |
| ua_find_callers | Find all callers of a specific function or file up to a certain depth. Helps trace execution paths. |
| ua_impact_analysis | Analyze the downstream impact of changing a specific file. Returns a list of files that depend on it. |
| ua_precheck | Pre-flight architectural risk check. Call this before modifying any critical systems or refactoring to estimate risk radius. |
| ua_rules | Evaluate architectural constraints against the current knowledge graph. Generates a full violation report. |
| ua_rules_check | Mid-session continuous audit. Evaluate constraints to ensure recent changes haven't introduced violations. |
| ua_init_rules | Initialize a starter .ua-rules.json file in the workspace if one doesn't already exist. |
| ua_ci_check | Run a CI-style impact analysis on a PR diff to identify risk factors. Returns affected files, risk level, and potential issues. |
| ua_validate_graph | Validate the structural integrity and syntax of the loaded knowledge graph JSON. |
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 clearly distinct purposes: one provides a module-level architecture breakdown, the other gives a high-level statistical summary of the graph. There is no overlap in their outputs, so an agent can reliably choose between them.
Both tools follow a consistent 'ua_<descriptive_name>' pattern in snake_case. The naming is predictable and clearly conveys each tool's function.
With only two tools, the server feels too limited for its stated purpose of codebase understanding. A well-scoped server for this domain would typically offer at least 5–10 tools to cover key operations like querying, searching, and exploring relationships.
The tool surface provides only high-level summaries (architecture and statistics). Essential operations for understanding a codebase—such as searching for specific nodes, exploring dependencies, or querying relationships—are missing, leaving significant gaps.