freelo-mcp-server (sesonet/freelo-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 58 out of 100, grade D. It declares 33 tools. No publisher has claimed this listing.

D
Caution
58/100

freelo-mcp-server

MCP server for Freelo project management API, enabling task, project, and time tracking management. Features 33 curated tools, readonly mode, and audit logging.

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

Code Verified⚡ Live Monitored: not connected

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

sesonet

Source: Glama

Is this your MCP?

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.

// key findings
⚠️
Known vulnerabilities in dependencies: 14 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
33 tools verified — handlers match their declared behaviour
20 read-only tools verified — handlers contain no write/delete/exec
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 1 credential: FREELO_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes33 tools

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.

freelo_get_all_comments

Fetches all comments across projects with filtering and sorting. Includes discussions on tasks, documents, files, and links.

freelo_get_note

Fetches a specific note by ID, including title, content, and metadata. Notes are standalone documents for project documentation.

freelo_create_note

Creates a new note in a project. Notes are standalone documents for project documentation, meeting minutes, or specifications.

freelo_update_note

Updates an existing note's title or content. All fields are optional - only provide what needs to change.

freelo_get_projects

Fetches your own active projects in Freelo. Returns only projects that you own. For all accessible projects, use freelo_get_all_projects.

freelo_get_all_projects

Fetches all projects in Freelo - both owned and shared. Supports pagination.

freelo_get_project_details

Fetches detailed information about a specific project including workers, tasklists, and settings.

freelo_get_project_workers

Fetches all workers (team members) assigned to a specific project.

freelo_search_elasticsearch

Performs full-text search across Freelo using Elasticsearch. Searches tasks, subtasks, projects, tasklists, files, and comments.

freelo_get_tasks_by_filter_uuid

Fetches tasks using a custom filter UUID. Custom filters are pre-configured task searches with multiple criteria.

freelo_get_all_states

Fetches all available task states in Freelo. States represent task lifecycle (1=active, 2=finished). Essential for state_id filters.

freelo_get_subtasks

Fetches all subtasks belonging to a parent task. Returns subtasks with their names, statuses, and assignments.

freelo_create_subtask

Creates a subtask under an existing task. Subtasks help break down complex tasks into smaller pieces.

freelo_get_project_tasklists

Fetches all tasklists within a project. Tasklists organize tasks into logical groups (e.g., "To Do", "In Progress", "Done"). Use after freelo_get_projects to drill down into project structure.

freelo_get_tasklist_details

Fetches detailed information about a specific tasklist including name, description, color, workers, and settings.

freelo_get_all_tasks

Fetches all tasks across all projects with filtering. Supports search, project/tasklist filter, label filter, date ranges, worker assignment, and pagination.

freelo_get_task_details

Fetches complete details about a specific task including name, description, assignees, due date, priority, status, labels, and metadata. Use after finding tasks with freelo_get_all_tasks.

freelo_get_task_description

Fetches only the description content of a task. More lightweight than freelo_get_task_details when you only need the description text.

freelo_get_finished_tasks

Fetches completed/finished tasks from a specific tasklist. For finished tasks across all projects, use freelo_get_all_tasks with state_id=2.

freelo_get_public_link

Generates or retrieves a public sharing link for a task. Anyone with this link can view task details without logging in.

freelo_create_task

Creates a new task in a specific tasklist. Task is created in active state.

freelo_create_task_from_template

Creates a new task based on an existing template task. The new task inherits the template's name, description, and structure.

freelo_edit_task

Updates an existing task. Can modify name, assignment, due date, or priority. For description updates, use freelo_update_task_description.

freelo_update_task_description

Updates only the description of a task. Supports plain text or markdown. Previous description is replaced completely.

freelo_finish_task

Marks a task as finished/completed. Task is moved to finished state, preserving all data. Can be reactivated with freelo_activate_task.

freelo_activate_task

Reactivates a finished task, moving it back to active state. Use when a completed task needs to be reopened.

freelo_start_time_tracking

Starts real-time time tracking for a task. Creates an active timer that runs until stopped with freelo_stop_time_tracking.

freelo_stop_time_tracking

Stops the currently active time tracking session. Calculates elapsed time and automatically creates a work report.

freelo_get_users

Fetches all users in the Freelo workspace. Returns user list with names, emails, IDs, and roles. Essential for getting user IDs before assigning tasks.

freelo_get_assignable_workers

Fetches users who can be assigned to tasks in a specific tasklist. Use before creating or assigning tasks to ensure the assignee has access.

freelo_get_work_reports

Fetches work reports (time entries) with filtering. Essential for billing, productivity analysis, and project reporting.

freelo_create_work_report

Creates a new work report (time entry) for a task. Use after completing work for timesheet entry.

freelo_update_work_report

Updates an existing work report. Use to correct time entries or add descriptions.

// known CVEs in dependencies14 high5 medium11 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.22.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.22.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.22.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

highaxios@1.12.2GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

highaxios@1.12.2GHSA-3g43-6gmg-66jw

axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretFREELO_API_KEYexport ="your-api-key"
configFREELO_AUDIT_ENABLEDfalse # Disable logging
configFREELO_AUDIT_LOG./logs/audit.jsonl # Log file path
configFREELO_AUDIT_WEBHOOKNo Webhook URL
configFREELO_EMAILexport ="your@email.com"
configFREELO_READONLYfalse freelo-mcp-server
// quality suggestions

All four hints declared on every tool

33/33 tools missing one or more hints — freelo_get_all_comments (missing: destructiveHint, idempotentHint, openWorldHint); freelo_get_note (missing: destructiveHint, idempotentHint, openWorldHint); freelo_create_note (missing: readOnlyHint, destructiveHint, openWorldHint), +30 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.

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 14 high severity in production deps — @modelcontextprotocol/sdk@1.22.0 (high), @modelcontextprotocol/sdk@1.22.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 3 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/sesonet/freelo-mcp-server?variant=verified)](https://m8ven.ai/mcp/sesonet/freelo-mcp-server)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 811120425c63050cb79a5ea992a75ad5cba4c4e8
code hash: d3c1b3cb5d0a2a99d9cb504fe368e3e7d9ab3fd763f385571d8e418ffddd6756
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client