Cursor Plan Executor (shanaka95/cursor-mem-mcp) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 15 tools. No publisher has claimed this listing.
A Model Context Protocol server for Cursor that manages and executes task plans with SQLite3-based CRUD operations, status tracking, and workflow tools.
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
shanaka95
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.
initialize_planInitialize a new task with your plan. Call this tool whenever you start a new task and already have the plan for it. Define all separate steps in the plan with validation criteria. Do not initialize a plan twice, as once initialized it will delete all previous plan data. Create the plan for the whol…
show_all_stepsShow all plan steps in a readable format with status indicators
get_next_stepGet the next pending step that you should follow
get_current_validation_criteriaGet the validation criteria for the currently unfinished task. This will list the validation criteria for the next pending step.
mark_current_step_doneMark the current (next pending) step as done. You should provide execution_data describing what was accomplished and any issues encountered.
mark_step_as_not_doneMark a specific step as not done (pending). Call this tool when you need to revert a completed step back to pending status.
update_step_dataUpdate the instructions and validation criteria for a specific step by step ID
insert_step_at_positionInsert a new planning step at a specific position. Can be used if you need to add extra steps after initialization. The tool will reorder existing steps properly according to step numbers.
update_step_execution_dataUpdate the execution data for a plan step (useful for tracking progress and notes)
get_plan_stepGet a specific plan step by step number with full details
delete_plan_stepDelete a plan step by step number
clear_all_plan_stepsClear all plan steps from the database (use with caution)
add_variableSave a variable that might be useful for later steps in the plan. Use this to store important information like file paths, configuration values, user preferences, or any data that will be needed in subsequent steps.
list_variablesList all stored variables with their names and descriptions. Use this to see what variables are available for use in current or future steps.
get_variableGet a specific variable's value and description by its name. Use this to retrieve stored information when needed for current or future steps.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Tool 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
15/15 tools missing one or more hints — initialize_plan (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); show_all_steps (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_next_step (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +12 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.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Production dependencies are patched
0 critical, 1 high severity in production deps — @modelcontextprotocol/sdk@0.4.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
1/3 production deps stale: sqlite@2023-11-01 (2.8y)
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/shanaka95/cursor-mem-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