This server provides Python code quality analysis and health scoring.
Run a comprehensive analysis combining complexity, dead code, clone detection, coupling (CBO), and dependency checks on a file or directory.
Check cyclomatic complexity of Python functions with configurable limits and details.
Analyze class coupling (CBO) metrics for Python code.
Detect code clones using similarity thresholds and minimum line counts.
Find unreachable/dead code using control-flow-graph analysis, filterable by severity.
Get an overall code health score (0–100) with grade and category scores.
Provides automatic session lifecycle management for Git repositories, including automated initialization, quality checkpoints, and session cleanup with learning capture.
Click on "Deploy 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., "@Session Buddy checkpoint the current session and analyze workflow efficiency"
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.
Session-Buddy is a session-lifecycle and memory MCP server for Claude Code and other MCP clients. It manages session startup, checkpoints, cleanup, searchable reflections, cross-project context, and quality signals through a local DuckDB-backed service.
Related MCP server: Claude Session MCP
Crackerjack is the canonical quality gate for repository changes. Use the focused checks while iterating and the full gate before handoff:
crackerjack lint
crackerjack typecheck
crackerjack security
crackerjack run --run-testsInitialize, checkpoint, inspect, and end sessions through MCP tools.
Detect Git repositories and perform lifecycle setup and cleanup automatically.
Create handoff context and capture learnings during checkpoints and session end.
Keep pre-compaction hooks and session state available to Claude Code.
For non-Git projects, the same lifecycle can be invoked explicitly through the MCP tools.
Store reflections and conversation context in DuckDB.
Search by text, concept, file, project, or time-oriented queries.
Reuse context across sessions and related repositories.
Use local text search without an embedding service; semantic search can use a configured HTTP provider such as llama-server or Ollama and degrades gracefully when no provider is available.
Project groups and dependency relationships let searches include related repositories and rank results using project context. This is useful for multi-repository services, monorepos, and coordinated development work.
Session-Buddy integrates with Crackerjack to record quality results, test patterns, failure resolutions, and workflow context. It also exposes health, Prometheus metrics, WebSocket monitoring, analytics commands, and signed skill/agent metadata for MCP clients.
Session-Buddy captures reflections during checkpoints and session cleanup using deterministic extraction and content-hash deduplication. Captured knowledge can then be retrieved through the memory and search tools.
The server also publishes signed capability metadata for MCP clients:
Skills: session_buddy_list_skills, session_buddy_get_skill
Agents: session_buddy_list_agents, session_buddy_get_agent
These catalogs describe available capabilities; they do not perform autonomous self-modification. See Insights Capture for the capture and retrieval details.
When the MCP server is connected from a Git repository, Session-Buddy can
initialize the session on connection and perform cleanup on disconnect. The
start, checkpoint, status, and end tools remain available for explicit
control, and non-Git projects use that explicit workflow by default.
stateDiagram-v2
[*] --> GitRepo: Claude Code Connects
[*] --> ManualInit: Non-Git Project
GitRepo --> AutoStart: Auto-detect Git
AutoStart: Initialize Session
AutoStart --> Working: Development
ManualInit --> ManualStart: User runs /start
ManualStart: Initialize Session
ManualStart --> Working: Development
state Working {
[*] --> Active
Active --> Checkpoint: /checkpoint
Checkpoint --> Active: Continue Work
Active --> Monitoring: Track Quality
Monitoring --> Active
}
Working --> AutoEnd: Disconnect/Quit
Working --> ManualEnd: User runs /end
AutoEnd: Auto Cleanup
AutoEnd --> [*]: Session Handoff
ManualEnd: Manual Cleanup
ManualEnd --> [*]: Session Handoff
The MCP server exposes a profile-gated tool surface through
SESSION_BUDDY_TOOL_PROFILE:
minimal — session lifecycle, basic search, hooks, health, baseline probes,
and published agent metadata.
standard — the daily-development surface, including conversation,
extraction, knowledge graph, Crackerjack, monitoring, cross-repository,
skills, and agent tools.
full — all registered tool groups; this is the default when the variable is
unset or invalid.
The active profile is defined in
session_buddy/mcp/tools/profiles.py.
The complete reference is in
docs/user/MCP_TOOLS_REFERENCE.md.
Always-available baseline tools include:
Tool | Purpose |
| List registered tools, optionally filtered by name substring |
| Return service, version, and uptime information |
| Probe configured dependencies |
| Return a dependency health summary |
Core session and memory tools include start, checkpoint, status, end,
store_reflection, quick_search, search_summary, search_by_file, and
search_by_concept.
The signed catalogs expose server-published capabilities through:
session_buddy_list_skills and session_buddy_get_skill
session_buddy_list_agents and session_buddy_get_agent
The HTTP service also provides /health, /healthz, and /metrics on the
main service port.
Crackerjack is Session-Buddy's quality and CI/CD integration point. Session- Buddy can retain quality results, test outcomes, failure patterns, and useful resolutions as session context so later checkpoints and sessions can retrieve them.
Typical local validation is:
crackerjack run --run-testsSee Crackerjack Integration for the MCP tools and integration details.
Python 3.14+
uv or pip
An MCP client that supports streamable HTTP
git clone https://github.com/lesleslie/session-buddy.git
cd session-buddy
uv sync
# Start the streamable HTTP MCP service on 127.0.0.1:8678
uv run session-buddy server startUseful lifecycle and diagnostics commands:
uv run session-buddy server status
uv run session-buddy server health
uv run session-buddy health
uv run session-buddy doctorThe service endpoint is http://127.0.0.1:8678/mcp. Add an HTTP entry to the
client configuration:
{
"mcpServers": {
"session-buddy": {
"type": "http",
"url": "http://127.0.0.1:8678/mcp"
}
}
}Core text search works without an embedding service. Semantic search uses a configured HTTP embedding provider such as llama-server or Ollama when one is available.
After the MCP client connects, use the session prompts and tools directly:
/session-buddy:start
/session-buddy:checkpoint
/session-buddy:quick_search
/session-buddy:store_reflection
/session-buddy:endThe primary MCP tools are start, checkpoint, status, end,
quick_search, search_summary, search_by_file, search_by_concept, and
store_reflection. Claude Code shortcuts such as /start, /checkpoint, and
/end may be generated under ~/.claude/commands/ after initialization.
Session-Buddy uses Oneiric's layered settings model together with the repository's flat YAML compatibility layer. The project files are:
settings/session-buddy.yaml — committed defaults
settings/local.yaml — gitignored checkout-local overrides
settings/lite.yaml and settings/standard.yaml — mode-specific defaults
Oneiric also checks user-level files:
${XDG_CONFIG_HOME:-~/.config}/session-buddy/config.yaml
${XDG_CONFIG_HOME:-~/.config}/session-buddy/local.yaml
Environment variables use the SESSION_BUDDY_ prefix. Nested settings use
double underscores, for example:
SESSION_BUDDY_LOG_LEVEL=DEBUG
SESSION_BUDDY__DATABASE_PATH=/tmp/session-buddy.duckdb
SESSION_BUDDY_TOOL_PROFILE=standardRuntime data defaults to ~/.claude/data/reflection.duckdb, logs to
~/.claude/logs/, and Oneiric snapshots to .oneiric_cache/ in the configured
cache location.
Core session and text-search workflows do not require an external service. Embedding providers, LLM providers, and ecosystem integrations are optional and configured through the same settings and environment layers.
Session-Buddy stores conversation context and reflections in a local DuckDB database by default. Text search, project filtering, time-aware retrieval, and reflection statistics are available locally. Semantic search is optional and uses a configured HTTP embedding provider when enabled. See Configuration for the default paths and overrides.
Start or connect the MCP server.
Run /session-buddy:start when explicit initialization is needed.
Use /session-buddy:checkpoint during longer work sessions.
Search prior work with /session-buddy:quick_search or
/session-buddy:search_summary.
Store important conclusions with /session-buddy:store_reflection.
Run /session-buddy:end when the session is complete.
When deployed inside the Bodai ecosystem, Session-Buddy works as the session-lifecycle and knowledge-capture layer for the Bodai components: Mahavishnu orchestration, Akosha cross-system analytics, Crackerjack quality signals, and the oneiric configuration and adapter patterns shared across components. The standalone install is unaffected — Bodai adds no special-case overrides; consumers connect through the same MCP tools and DuckDB-backed store they would in any other Claude Code environment.
Check the service and dependency probes first:
uv run session-buddy server status
uv run session-buddy health --json
uv run session-buddy doctor --jsonIf the MCP client cannot connect, confirm that the service is listening on
127.0.0.1:8678 and that the client URL ends in /mcp. Use
SESSION_BUDDY_LOG_LEVEL=DEBUG for more detailed logging.
For memory or embedding issues, start with text search and then verify the
configured embedding provider and its endpoint. For configuration problems,
check the project YAML files, the Oneiric XDG files, and the effective
SESSION_BUDDY_* environment variables.
BSD 3-Clause License. See LICENSE.
Session-Buddy is built on open-source foundations including FastMCP, Oneiric, mcp-common, DuckDB, Typer, and Prometheus client.
Comprehensive Python code quality analysis with complexity, dead code, clone detection, and coupling metrics
| Name | Required | Description | Default |
|---|---|---|---|
| analyses | No | Array of analyses to run. Options: complexity, dead_code, clone, cbo, deps. Default: all analyses | |
| path | Yes | Path to Python code (file or directory) to analyze | |
| recursive | No | Recursively analyze directories (default: true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide key behavioral hints (destructiveHint: true, readOnlyHint: false, etc.), so the description doesn't need to repeat these. It adds value by specifying the types of analyses performed (complexity, dead code, etc.), but doesn't elaborate on side effects, rate limits, or output format beyond what annotations cover.
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, efficient sentence that front-loads the purpose and lists key analyses without unnecessary details. Every word contributes to understanding the tool's scope, making it highly concise and well-structured.
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?
Given the tool's complexity (multiple analysis types, destructive hint) and lack of output schema, the description is adequate but incomplete. It covers what analyses are performed but doesn't explain output format, error handling, or how results are returned, leaving gaps for an agent to invoke it correctly.
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%, so parameters are well-documented in the schema. The description adds minimal semantics by listing analysis types (e.g., complexity, dead_code) that align with the enum options, but doesn't provide additional context beyond what the schema already specifies.
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 performs 'Python code quality analysis' with specific metrics (complexity, dead code, clone detection, coupling), which is a specific verb+resource. However, it doesn't explicitly differentiate from sibling tools like check_complexity or detect_clones, which appear to handle individual analyses.
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 no guidance on when to use this tool versus its siblings. It mentions 'comprehensive' analysis but doesn't specify scenarios where this is preferred over individual analysis tools like check_complexity or detect_clones, nor does it mention prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Analyze cyclomatic complexity of Python functions
| Name | Required | Description | Default |
|---|---|---|---|
| max_complexity | No | Maximum allowed complexity, 0 = no limit (default: 0) | |
| min_complexity | No | Minimum complexity to report (default: 1) | |
| path | Yes | Path to Python code to analyze | |
| show_details | No | Include detailed metrics (default: true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructiveHint=true, readOnlyHint=false, openWorldHint=true, and idempotentHint=false, covering key behavioral traits. The description adds no additional context about what gets destroyed, authentication needs, rate limits, or other behaviors beyond annotations, but it doesn't contradict them, so it meets the lower bar with annotations present.
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, efficient sentence that directly states the tool's purpose without any fluff or redundancy. It is appropriately sized and front-loaded, making it easy to parse quickly.
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?
Given the tool's moderate complexity (4 parameters, no output schema) and rich annotations, the description is minimally adequate. It covers the basic purpose but lacks details on output format, error handling, or integration with sibling tools, which could help the agent use it more effectively in context.
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 all parameters well-documented in the schema. The description adds no extra meaning beyond the schema, such as explaining interactions between parameters or practical usage examples, so it defaults to the baseline score of 3.
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 action ('analyze') and resource ('cyclomatic complexity of Python functions'), providing a specific purpose. However, it doesn't differentiate from sibling tools like 'analyze_code' or 'find_dead_code', which might also analyze Python code metrics, so it doesn't fully distinguish from alternatives.
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 no guidance on when to use this tool versus alternatives such as 'analyze_code' or 'check_coupling'. It lacks context about specific scenarios, exclusions, or prerequisites, leaving the agent without clear usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Analyze class coupling (CBO - Coupling Between Objects) metrics
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path to Python code to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide key behavioral hints: readOnlyHint=false, destructiveHint=true, openWorldHint=true, and idempotentHint=false. The description doesn't contradict these annotations, and it adds context by specifying the type of analysis (CBO metrics). However, it doesn't elaborate on what 'destructive' means in this context (e.g., whether it modifies files or just analyzes them), which could be useful. No annotation contradiction is present.
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, concise sentence: 'Analyze class coupling (CBO - Coupling Between Objects) metrics.' It is front-loaded with the core purpose and uses no unnecessary words, making it efficient and easy to understand. Every part of the sentence contributes directly to clarifying the tool's function.
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?
Given the tool's complexity (analyzing code metrics), annotations cover behavioral aspects like destructiveness and idempotency, and the schema fully documents the single parameter. However, there is no output schema, so the description doesn't explain return values or results, which is a gap. The description is adequate but could benefit from more context on what the analysis entails or outputs.
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 has 100% description coverage, with the 'path' parameter clearly documented as 'Path to Python code to analyze.' The description doesn't add any extra meaning beyond this, such as format examples or constraints. Given the high schema coverage, a baseline score of 3 is appropriate, as the schema handles the parameter documentation adequately.
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's purpose: 'Analyze class coupling (CBO - Coupling Between Objects) metrics.' It specifies the verb 'analyze' and the resource 'class coupling metrics,' which is specific and informative. However, it doesn't explicitly distinguish this tool from its siblings like 'analyze_code' or 'check_complexity,' which prevents a score of 5.
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 no guidance on when to use this tool versus alternatives. It doesn't mention any context, prerequisites, or exclusions, nor does it reference sibling tools like 'analyze_code' or 'check_complexity' for comparison. This lack of usage instructions makes it difficult for an agent to select the right tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Detect code clones using APTED tree edit distance and LSH acceleration
| Name | Required | Description | Default |
|---|---|---|---|
| group_clones | No | Group related clones together (default: true) | |
| min_lines | No | Minimum lines to consider as clone (default: 5) | |
| path | Yes | Path to Python code to analyze | |
| similarity_threshold | No | Minimum similarity threshold 0.0-1.0 (default: 0.8) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate this is a destructive, non-idempotent, non-read-only operation with open-world data. The description adds value by specifying the algorithms used (APTED and LSH), which helps the agent understand computational behavior, but doesn't elaborate on side effects, rate limits, or output format beyond what annotations imply.
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, efficient sentence with zero waste. It front-loads the core purpose ('Detect code clones') and adds technical details (algorithms) that are relevant for agent understanding, making it appropriately sized and well-structured.
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?
Given the tool's complexity (destructive analysis with multiple parameters) and lack of output schema, the description is minimal. It covers the purpose and methods but omits details on output format, error handling, or performance considerations, leaving gaps for the agent to navigate.
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 clear parameter descriptions in the schema. The description adds no additional parameter semantics beyond implying analysis of Python code via 'path', which is already covered. Baseline 3 is appropriate as the schema handles parameter documentation adequately.
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's purpose: 'Detect code clones' using specific algorithms (APTED tree edit distance and LSH acceleration). It specifies the resource (Python code) and method, but doesn't explicitly differentiate from sibling tools like 'find_dead_code' or 'analyze_code' beyond the clone detection focus.
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?
No guidance is provided on when to use this tool versus alternatives like 'find_dead_code' or 'analyze_code'. The description lacks context about use cases, prerequisites, or exclusions, leaving the agent to infer usage based solely on the tool name and purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find unreachable code using Control Flow Graph (CFG) analysis
| Name | Required | Description | Default |
|---|---|---|---|
| min_severity | No | Minimum severity: info, warning, error (default: warning) | |
| path | Yes | Path to Python code to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructiveHint: true, readOnlyHint: false, openWorldHint: true, and idempotentHint: false, suggesting this tool performs mutable, non-idempotent operations with potential side effects. The description adds value by specifying the analysis method ('CFG analysis'), but it doesn't elaborate on what 'destructive' entails (e.g., modifies files, generates reports) or other behavioral traits like rate limits or authentication needs. With annotations covering key aspects, the description provides some context but lacks depth.
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, efficient sentence: 'Find unreachable code using Control Flow Graph (CFG) analysis'. It is front-loaded with the core purpose and method, with no unnecessary words or redundancy. Every part of the sentence contributes directly to understanding the tool's function, making it highly concise and well-structured.
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?
Given the tool has annotations (including destructiveHint: true) but no output schema, the description is moderately complete. It specifies the analysis method ('CFG analysis'), which adds context beyond the annotations. However, it doesn't explain the output format, potential side effects from the destructive hint, or how results are returned, leaving gaps that could hinder an AI agent's understanding of the full tool behavior.
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 clear descriptions for both parameters: 'min_severity' (minimum severity level with default) and 'path' (path to Python code). The description doesn't add any semantic details beyond the schema, such as explaining how 'CFG analysis' interacts with these parameters or providing examples. Given the high schema coverage, a baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.
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's purpose: 'Find unreachable code using Control Flow Graph (CFG) analysis'. It specifies the verb ('Find'), resource ('unreachable code'), and method ('CFG analysis'), making the intent unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'analyze_code' or 'detect_clones', which might also analyze code structure, so it misses the highest score.
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 no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, exclusions, or comparisons to sibling tools such as 'check_complexity' or 'detect_clones'. Without this context, an AI agent might struggle to choose this tool appropriately in a multi-tool environment.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get overall code health score (0-100) with grade and category scores
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path to Python code to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructiveHint=true and readOnlyHint=false, suggesting potential side effects, but the description doesn't explain what gets destroyed or altered (e.g., if analysis modifies files or consumes resources). It adds context about the output format (score range, grade, categories), which is useful since there's no output schema, but fails to address the destructive behavior hinted by annotations.
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, efficient sentence that front-loads the core purpose and includes key output details. Every word adds value without redundancy, making it easy for an agent to parse quickly.
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 tool with one parameter and no output schema, the description covers the basic purpose and output format adequately. However, given the annotations hint at destructive behavior and the lack of usage guidelines or behavioral details, it leaves gaps in understanding when and how to use the tool safely, especially compared to siblings.
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 has 100% description coverage, clearly documenting the 'path' parameter. The description doesn't add any parameter-specific details beyond what the schema provides, such as path format examples or constraints. With high schema coverage, a baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.
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 action ('Get') and the resource ('overall code health score') with specific output details (0-100 range, grade, category scores). It distinguishes from siblings by focusing on a comprehensive health metric rather than specific analyses like complexity or dead code detection, though it doesn't explicitly name alternatives.
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?
No guidance is provided on when to use this tool versus its siblings (e.g., analyze_code, check_complexity). The description implies a broad health assessment, but it doesn't specify use cases, prerequisites, or exclusions, leaving the agent to infer context from tool names alone.
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.
v0.14.3analyze_codecheck_complexitycheck_couplingdetect_clonesfind_dead_codeget_health_scoreScored across 6 tools
The tools have overlapping purposes that could cause confusion, particularly between analyze_code and the more specific tools like check_complexity and check_coupling. While descriptions clarify their focus, an agent might struggle to choose between analyze_code (which includes complexity and coupling) and the dedicated tools, leading to potential misselection.
All tool names follow a consistent verb_noun pattern (e.g., analyze_code, check_complexity, detect_clones), using snake_case throughout. This predictability makes it easy for agents to parse and understand the naming conventions without confusion.
With 6 tools, the count is well-scoped for a code analysis server, covering key aspects like complexity, coupling, clones, and dead code. Each tool appears to earn its place without feeling excessive or insufficient for the domain.
The tool set provides good coverage for code quality analysis, including metrics, clone detection, and dead code. A minor gap exists in areas like code style or security analysis, but agents can likely work around this with the available tools for core workflows.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Local-first, governed memory and session continuity for AI coding agents. No cloud, no telemetry.
Shared memory for coding agents. Stop re-explaining your codebase every session.