agentic-cal (talalakkari/agentic-cal) is an MCP server listed on the M8ven Trust Index. It scores 52 out of 100, grade D. It declares 20 tools. No publisher has claimed this listing.
Unified email and calendar management with AI agent, supporting email operations, calendar availability, and time blocking via MCP 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
talalakkari
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.
list_mailboxesList all available mailboxes
list_emailsList emails in a mailbox folder. Returns email metadata (id, subject, sender, recipient, date, read/starred status, thread_id).
get_emailGet a single email with its full body content. Use this to read the actual content of an email.
get_threadGet all emails in a conversation thread. Returns all messages sorted chronologically.
search_emailsSearch for emails matching a query across subject and body fields.
draft_replyDraft a reply to an email and save it to the Drafts folder. Does NOT send — saves a draft for review.
create_draftCreate a new draft email. Can be a new email or a reply draft.
update_draftUpdate an existing draft email's content.
delete_emailPermanently delete an email by ID.
send_replySend a reply to an email. Only call after drafting and getting confirmation.
send_emailSend a new email (not a reply). Only call after getting confirmation.
mark_email_readMark an email as read or unread.
move_emailMove an email to a different folder (inbox, sent, draft, archive, trash).
get_availabilityGet busy intervals across all calendars (Proton/Outlook/iCloud feeds plus agent-created blocks) for a time window. feed_warnings lists feeds whose data is stale or erroring — caveat answers accordingly. Events only exist within -7/+90 days of now.
find_free_slotsFind free time slots of at least duration_minutes within a window, intersected with working hours (default 08:00-18:00 America/Los_Angeles). Each returned slot is a full free gap — any start time with start + duration <= slot end fits. Sorted, max 20 slots.
block_timeBlock time across ALL calendars by emailing standards-compliant invites (iMIP) to each account. Asynchronous: returns immediately with status 'pending' (the slot counts as busy right away); acceptance per account is tracked by a workflow — check with get_block_status. Refuses with the conflict list …
get_block_statusGet a block's status (pending | partial | confirmed | cancelled) and per-account acceptance state (ACCEPTED | DECLINED | TENTATIVE | NEEDS-ACTION).
cancel_blockCancel a block: sends METHOD:CANCEL with a bumped SEQUENCE to every account (calendars remove the event) and stops the acceptance workflow.
list_blocksList agent-created blocks, optionally filtered by time window and status (pending | partial | confirmed | cancelled).
list_calendarsList the registered calendar feeds and their ingest health: id, label, detail_level (busy|full), event_count (events currently in the -7/+90 day window), last_fetched/last_changed (ISO 8601 or null), stale_hours (-1 = never fetched), fresh (recently fetched AND no error), and last_error. Read-only. …
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Drizzle ORM has SQL injection via improperly escaped SQL identifiers
Hono JWK Auth Middleware has JWT algorithm confusion when JWK lacks "alg" (untrusted header.alg fallback)
hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard
Hono JWT Middleware's JWT Algorithm Confusion via Unsafe Default (HS256) Allows Token Forgery and Auth Bypass
vite: `server.fs.deny` bypass on Windows alternate paths
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
20/20 tools missing one or more hints — list_mailboxes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_emails (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_email (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 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.
Tool inputs are validated
17/20 tool handlers declare input schemas (85%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 0/20 tool handlers wrap calls in try/catch (0%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
23 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 4 high severity in production deps — drizzle-orm@0.45.1 (high), hono@4.7.11 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
2 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
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/talalakkari/agentic-cal)?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