When was api.lmgram.com last audited?

Last checked 2026-10-28; wmcp.sh re-checks it on a schedule for tool drift and rug-pulls.

api.lmgram.com

Item: api.lmgram.com
Rating: 45
Author: wmcp.sh

https://api.lmgram.com/mcp

45/100 · MCP Trust Grade · checked 2d ago · MCP 2025-03-26

Is the api.lmgram.com MCP server safe to use?

Independent trust grade F (45/100). Tool "panel_sync_device_keys" references sensitive file paths / secrets (exfiltration surface). wmcp.sh continuously watches api.lmgram.com for tool drift and rug-pulls. The grade is free and identical whether or not the operator pays.

⚠ Rug-pull watch: this server's tool surface has changed 2× since baseline — last 26d ago. Continuously watched by wmcp.sh for drift & rug-pulls.

What it offers — 17 tools · Social & Comms

get_current_user

Returns the LMGram profile linked to the connected account.

request_human_match

Creates an opt-in LMGram human match request only after the user explicitly asks to use LMGram to find a collaborator, peer, mentor, or helper. Never

list_match_requests

Lists recent match requests for the current LMGram user, optionally filtered by role and status.

start_chat

Starts a LMGram chat for a match request, or records that this side wants to chat.

list_messages

Lists messages in a LMGram chat. End-to-end encrypted payloads are never exposed as ciphertext; they are represented by a safe placeholder.

send_message

Sends a message into a LMGram chat.

open_lmgram_panel

Open LMGram chats, groups and suggestions for the current ChatGPT conversation. Each conversation has a separate context; never copy a transcript or p

panel_snapshot

Refresh this conversation's private panel data.

panel_chat

Retrieve authorized chat data for client-side decryption, not model context.

panel_register_device

panel_mark_read

Mark the displayed chat as read.

panel_sync_device_keys

Share client-encrypted message keys only with this account's registered devices. Does not send messages, plaintext or private keys.

panel_send_message

Send a client-encrypted text message after the user presses Send. Retry only the identical payload and clientMessageId.

panel_start_chat

Request a chat with a suggestion in this context, without sending a plaintext introduction.

panel_dismiss_suggestion

Decline an unopened match suggestion.

panel_join_group

Accept an existing group invitation related to this context.

panel_create_intent

Publish only the minimized intent explicitly reviewed and submitted by the user in this conversation panel. Do not include secrets, private transcript

Spec conformance20%100

✓ initialize → protocolVersion 2025-03-26
✓ initialize HTTP 200
✓ unknown method → -32601
✓ tools/list → 17 tools
✓ every tool has name + inputSchema

Security (OWASP MCP)30%10

17 tools scanned
no injection markup
1 secret-path refs

Reliability / performance20%92

single-probe latency 141ms (PRELIMINARY — continuous uptime/p95 from proxy telemetry lands in v2)

Tool hygiene15%76

88% of tools have typed inputSchema
11/17 declare outputSchema
2 destructive-by-name tools lack safety annotations

Transparency / provenance15%90

HTTPS ✓
RFC 9728 oauth-protected-resource metadata ✓
advertises protocol 2025-03-26

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

FAILMCP08 Tool "panel_sync_device_keys" references sensitive file paths / secrets (exfiltration surface).

Developers see this F before they connect to api.lmgram.com.

Clear it: a Deep Audit shows exactly what to fix, and Monitoring proves the fix to everyone who checks your grade. Drop your email and we'll send this server's full findings + the fix path. The grade itself stays free.

Grade another server

We re-grade api.lmgram.com on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Run api.lmgram.com? Claim it (free) to get drift alerts and show an independently-verified trust badge. The grade stays free — claiming just ties it to you.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — api.lmgram.com grade F

Share on X Open card image

https://wmcp.sh/mcp/grade/api.lmgram.com

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade F](https://wmcp.sh/mcp/grade/api.lmgram.com/badge.svg)](https://wmcp.sh/mcp/grade/api.lmgram.com)

HTML

<a href="https://wmcp.sh/mcp/grade/api.lmgram.com"><img src="https://wmcp.sh/mcp/grade/api.lmgram.com/badge.svg" alt="MCP Trust Grade F · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.