starlog-mcp
STARLOG is a documentation workflow MCP server for Claude Code that manages project rules, debug diaries with GitHub issue integration, and session tracking for context continuity.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
sancovp
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
init_projectCreates project structure with registries and HPI template. Use this when check() shows directory is not a STARLOG project. Args: path: Directory path for the STARLOG project name: Project name description: Project description giint_project_id: Optional GIINT project ID to link this STARLOG project …
checkVerifies if directory is a STARLOG project. Always use this first to determine if you need to init_project or can proceed with orient.
orientReturns full Captain's Log XML context for existing projects. Use this after check() confirms project exists to get complete project history and context.
rulesView project guidelines and standards. Use this to check what coding standards and project rules have been established.
update_rulesReplace all project rules with RulesEntry models.
add_ruleCreate new project guideline or standard. Use this to establish coding standards, project conventions, or other guidelines during development.
delete_ruleRemove specific rule.
view_debug_diaryCheck current project status and recent entries. Use this to review what's been discovered and logged during the current session.
update_debug_diaryLog real-time discoveries, bugs, insights during work. Use this frequently during your work session to track progress and issues.
view_starlogGet registry paths where starlog data is stored. Returns the actual file paths to access the raw session data.
start_starlogBegin tracked development session with goals and context. Use this to start a new work session after orient() provides project context.
end_starlogComplete session with summary and outcomes. Use this to properly close your work session with a summary of what was accomplished.
retrieve_starlogSelective historical retrieval.
starlog_guideReturns STARLOG system workflow and tool usage guide.
query_project_rulesQuery project rules brain for development guidance based on context. Args: path: Project path containing STARLOG rules context: Development context/question to query persona_id: Predefined persona ID. Available personas: - 'logical_philosopher': Rigorous logical analysis with explicit premises - 'se…
list_most_recent_projectsList most recently used STARLOG projects with pagination.
HEAVEN_DATA_DIRDirectory for STARLOG data storage (default: /tmp/heaven_data)LLM_INTELLIGENCE_DIRTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
16/16 tools missing one or more hints — init_project (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); orient (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — orient (line 70: with open(COURSE_STATE_FILE, 'w') as f:)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
15/16 tool handlers declare input schemas (94%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 4/16 tool handlers wrap calls in try/catch (25%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Tool description accuracy
orient: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/sancovp/starlog-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check