sugar
Persistent memory for AI coding agents. Local-first, cross-session context, global knowledge, and optional autonomous task execution.
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
roboticforce
Source: PulseMCP · also listed on github_topic, 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.
createTaskCreate a new Sugar task for autonomous development
listTasksList Sugar tasks with optional filtering
viewTaskView detailed information about a specific task
updateTaskUpdate an existing Sugar task
removeTaskRemove a task from the queue
getStatusGet Sugar system status and task queue metrics
runOnceExecute one autonomous development cycle (picks up highest priority task)
initSugarInitialize Sugar in the current project directory
analyze_issueAnalyze a GitHub issue and return insights
generate_responseGenerate a response for a GitHub issue
search_codebaseSearch the codebase for relevant code
find_similar_issuesFind issues similar to a given issue
suggest_labelsSuggest labels for an issue based on its content
validate_responseValidate a response before posting
search_memorySearch Sugar memory for relevant context.
store_learningStore a new learning, decision, or observation in Sugar memory.
get_project_contextGet current project context summary from Sugar memory.
recallGet memories about a specific topic, formatted as readable context.
list_recent_memoriesList recent memories from both project and global stores, optionally filtered by type.
sugar_add_taskAdd a new task to the Sugar work queue for autonomous execution.
sugar_list_tasksList tasks in the Sugar work queue with optional filtering.
sugar_view_taskGet detailed information about a specific task.
sugar_update_taskUpdate properties of an existing task.
sugar_task_statusGet queue statistics and system health information.
sugar_remove_taskRemove a task from the work queue.
sugar_quality_gate_checkRun quality gate checks
sugar_learning_queryQuery the learning system
spawn_subagentSpawn a single sub-agent to execute a task.
spawn_parallel_subagentsSpawn multiple sub-agents to execute tasks in parallel.
SUGAR_DEBUGSUGAR_PROJECT_ROOTSUGAR_MODELANTHROPIC_API_KEYGITHUB_TOKENSUGAR_DEFAULT_REPOOPENCODE_CONFIGOPENCODE_CONFIG_DIRGITHUB_EVENT_PATHGITHUB_OUTPUTGITHUB_REPOSITORYSUGAR_PROJECT_DIRSUGAR_SYNC_TURNSSUGAR_SEARCH_LIMITOPENCODE_SERVER_URLOPENCODE_API_KEYOPENCODE_TIMEOUTSUGAR_OPENCODE_ENABLEDTool 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
30/30 tools missing one or more hints — createTask (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); listTasks (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); viewTask (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +27 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
3 tools describe read intent but their handlers mutate — listTasks (line 39: spawn(command, args, {); viewTask (line 39: spawn(command, args, {); getStatus (line 39: spawn(command, args, {)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
23/24 tool handlers declare input schemas (96%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
23/30 tools referenced in tests (77%)
Write tests that reference each tool by name so every tool has at least one test.
Tool description accuracy
3 tools have description/behavior mismatches: listTasks: description implies read-only but handler writes/deletes/executes; viewTask: description implies read-only but handler writes/deletes/executes; getStatus: 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/roboticforce/sugar)?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