Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sove-mcp Analyze the dependency graph and find circular dependencies in my project."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that gives Claude structural understanding of a codebase — dependency graph, entry points, complexity ranking and import cycles — without reading every file into context.
Claude can already read files. But answering "what are the entry points, and which five modules are most complex?" means pulling the whole repository into the context window. On a 145-file application that is tens of thousands of tokens, most of it irrelevant.
This computes the answer locally and returns a few hundred tokens:
{
"files": 35,
"dependencyEdges": 83,
"circularDependencies": 0,
"entryPoints": [{ "file": "cli/index.ts", "dependencies": 5 }],
"mostComplex": [
{ "file": "phases/phase2-ghostwriter/test-generator.ts", "cyclomatic": 105, "cognitive": 95 }
]
}Built on sove-toolkit, which resolves
CommonJS require(), ESM imports, and TypeScript path aliases (@/components/Button).
Related MCP server: code-context
npm install -g sove-mcpAdd to your MCP client config. For Claude Desktop, claude_desktop_config.json:
{
"mcpServers": {
"sove": {
"command": "sove-mcp",
"env": {
"SOVE_MCP_ALLOWED_ROOTS": "/path/to/your/projects"
}
}
}
}For Claude Code:
claude mcp add sove -e SOVE_MCP_ALLOWED_ROOTS=/path/to/your/projects -- sove-mcpTool | Returns |
| Full summary: files, edges, entry points, cycles, complexity |
| Modules nothing imports — where execution starts |
| Import cycles, via Tarjan's algorithm, with severity |
| Cyclomatic and cognitive complexity ranking |
| Writes JSDoc into source files — opt-in only, see below |
All tools take a directory. Everything except the last is read-only and annotated as
such, so clients can surface that to the user.
An MCP server runs with the privileges of whoever launched it, and the model decides what to call. Two defaults follow from that:
Reads are confined to allowed roots. SOVE_MCP_ALLOWED_ROOTS (path-separator
delimited) defines what the server may read; it defaults to the working directory. Paths
are compared with path.relative, not string prefixes — /data-private starts with
/data as a string but is not inside it, and a prefix check would let it through.
Nothing writes unless you opt in. generate_documentation modifies source files, so
it is not registered at all unless SOVE_MCP_ALLOW_WRITES=true. A default install cannot
alter your files regardless of what the model is asked to do.
SOVE_MCP_ALLOWED_ROOTS="/home/me/work:/home/me/side" SOVE_MCP_ALLOW_WRITES=true sove-mcpnpm install
npm test # 12 tests, driven over real stdio JSON-RPC
npm startThe tests spawn the actual server process and speak JSON-RPC to it rather than calling handlers directly — that is the only way to catch schema-registration, transport and startup faults, which is where servers like this actually break.
MIT
Builds a dependency graph for a codebase and returns a summary: file count, import edges, entry points, circular dependencies and the most complex modules. Use this instead of reading every file when you need architectural context.
| Name | Required | Description | Default |
|---|---|---|---|
| directory | Yes | Absolute or relative path to the source directory to analyse |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description doesn't need to cover safety. It adds value by specifying exactly what the tool returns and that it computes a dependency graph, providing useful behavioral context beyond the annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the action and output, followed by a usage recommendation. Every word earns its place, with no redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description includes a comprehensive list of returned summary items, serving as a form of output documentation since no output schema exists. It also gives usage context. It could mention limitations (e.g., language support or scalability) or explicitly contrast with sibling tools, but overall it is sufficiently complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single 'directory' parameter, so the schema already documents it fully. The description does not add any parameter-specific details beyond what is in the schema, matching the baseline for full coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool 'Builds a dependency graph for a codebase' and lists specific outputs (file count, import edges, entry points, circular dependencies, most complex modules). This distinguishes it from sibling tools that focus on individual analyses, making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit usage guidance: 'Use this instead of reading every file when you need architectural context.' This tells the agent when to invoke it, though it does not explicitly mention alternatives or when not to use it. The guidance is clear but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Detects import cycles using Tarjan's algorithm. Returns each cycle with a severity based on how many modules it spans.
| Name | Required | Description | Default |
|---|---|---|---|
| directory | Yes | Absolute or relative path to the source directory to analyse |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool as read-only, so the description does not need to restate that. It adds valuable behavioral context by specifying the algorithm (Tarjan's) and the return behavior (each cycle with severity based on module span), which goes beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only two sentences, front-loaded with the main action ('Detects import cycles') and includes essential details without filler. Every clause adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has one well-documented parameter, clear return behavior despite no output schema, and read-only annotations. The description is sufficient for an agent to understand what it does and what it returns. Minor caveats about performance or input structure are not critical for this simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers the single parameter 'directory' with 100% description coverage, so the schema already provides the needed meaning. The description does not add extra parameter semantics beyond what the schema states, making the baseline 3 appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Detects' with a clear resource 'import cycles', and it distinguishes itself from siblings like find_entry_points and most_complex_files by focusing on dependency cycles, not general analysis or complexity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies when to use this tool (to detect circular imports), but it does not explicitly state alternatives or when not to use it. The context is clear enough for an agent to select it appropriately among sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Lists the modules nothing else imports — where execution starts. Useful for orienting in an unfamiliar codebase before reading any source.
| Name | Required | Description | Default |
|---|---|---|---|
| directory | Yes | Absolute or relative path to the source directory to analyse |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds the core selection criterion (modules not imported) and the interpretation of entry points. This goes beyond the annotations, though it does not describe return format or edge cases, so not a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences, front-loaded with the core behavior and followed by a practical use case. Every word earns its place with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only tool with one well-documented parameter and strong annotations, the description is complete. It explains what the tool outputs (a list of modules) and when to use it, which is sufficient without an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the `directory` parameter fully documented. The tool description adds no parameter-level detail, so the baseline of 3 is appropriate since the schema carries the load.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists modules that nothing else imports, identifying entry points where execution starts. This specific verb+resource distinguishes it from sibling tools like find_circular_dependencies and most_complex_files.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear use case: 'Useful for orienting in an unfamiliar codebase before reading any source.' It does not explicitly mention alternatives or when not to use it, but the context is clear enough for an agent to decide appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Ranks modules by cyclomatic complexity so you can find refactoring targets without reading the codebase.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many files to return (1-50) | |
| directory | Yes | Absolute or relative path to the source directory to analyse |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the core behavioral trait: ranking modules by cyclomatic complexity. Annotations already mark it as read-only, so no safety contradictions exist. While it does not detail traversal or filtering behavior, the metric and ranking intent are clearly stated, which is sufficient for a simple read-only analysis tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 15 words, front-loaded with the action verb. It efficiently conveys both the operation and the motivation without unnecessary repetition or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is straightforward, and the description, combined with the well-documented schema and read-only annotation, gives enough context. There is no output schema, but the ranking nature implies the return format, and the description's 'ranks' likely implies an ordered list. No major gaps are evident for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for both parameters (directory and limit) with 100% coverage. The description itself does not add any additional meaning about parameters, so it meets the baseline of 3 without exceeding it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Ranks') and resource ('modules') and identifies the exact metric (cyclomatic complexity) and purpose (finding refactoring targets). This clearly distinguishes it from sibling tools like find_entry_points or find_circular_dependencies, which focus on different aspects of code analysis.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'so you can find refactoring targets' provides a clear context for when to use the tool. However, it does not explicitly mention alternatives or when not to use it, though the specificity of complexity ranking implicitly separates it from siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0analyze_repositoryfind_circular_dependenciesfind_entry_pointsmost_complex_filesEach tool targets a distinct analysis aspect, but analyze_repository overlaps by summarizing entry points, cycles, and complexity, which are also covered by the specialized tools. The descriptions clarify that the summary is high-level, while the other tools provide deeper dives.
Three tools use verb_noun naming (analyze_repository, find_entry_points, find_circular_dependencies), but most_complex_files is an adjective phrase, breaking the pattern. All names use snake_case, maintaining readability despite the inconsistency.
Four tools is well-scoped for a code analysis server, falling within the ideal 3-15 range. Each tool serves a distinct purpose in architectural analysis, and the count feels neither thin nor bloated.
The set covers the key aspects of codebase analysis: overall summary, entry points, circular dependencies, and complexity. Minor gaps exist (e.g., dependency depth, module coupling), but the core workflows for architectural understanding are complete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
An MCP server that gives your AI access to the source code and docs of all public github repos
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
MCP server giving Claude AI access to 22+ NYC public-record databases for real estate due diligence
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/JrKrishh/sove-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
