io.github.saezbaldo/lmgram

MCPcommunitylive
v0.1.2io.github.saezbaldoUnknownUpdated 2mo ago

Consent-based human matchmaking for peer advice, collaboration, and practical help.

Endpoint healthlive
checked 5 days ago · 228ms
100% of the last 5 checks reached this endpoint
Works in
ClaudeCursorCopilotChatGPTGemini

Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
2mo agoLast update
Package
Authorio.github.saezbaldo
LicenseUnknown
Version0.1.2
Sourcemcp-registry
Trust Status
D
30/100Risk
✓Listed in Forge index+10/10
—Publisher identity verified+0/30
→ Publisher: this listing has no repository on file, so `forge publish` cannot verify ownership automatically. Use "Claim this listing" above — Forge reviews these by hand.
—Domain verification+0/10
→ Not currently available for this listing type — the domain-verification check only runs for npm-backed packages today, so this row cannot be earned here yet regardless of what's hosted at the domain.
—Prompt-injection scan · findings+0/30
→ Publisher: remove instructions in the source aimed at AI clients rather than human readers
✓Obfuscation / exfil scan · clean+20/20
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
DependenciesNot audited
Tool surface6 tools · none privileged
Security scan⚠ Warnings (1)vlive · 15d agoHow well does this scan work?
PROMPTtool:request_human_match#summaryExfiltration-shaped instruction
EvalsNone
IndexedJul 23, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

6 tools · none privileged · 1 flagged for injection
Observed live from the vendor's endpoint15d ago

Read from a real MCP initialize → tools/list handshake against the declared endpoint. No tool was ever invoked — tools/list is the read-only introspection call the protocol defines for this. It reflects what the server advertised at that moment; a hosted endpoint is not pinned to any version and can change without notice.

  • https://api.lmgram.com/mcp6 tools · 216ms
get_current_userReturns the LMGram profile linked to the connected account.

Returns the LMGram profile linked to the connected account.

No input schema was published for this tool.

request_human_matchinjection riskCreates 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 invoke for general advice, dating or romantic matchmaking. Never include secrets, credentials, API keys, raw transcripts, customer data, or private d…

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 invoke for general advice, dating or romantic matchmaking. Never include secrets, credentials, API keys, raw transcripts, customer data, or private d…

INJECTIONIn parameter summary: Exfiltration-shaped instruction non-sensitive summary. Never send secrets, credentials, API keys, raw transcripts, customer da
ParameterTypeDescription
topic*stringShort, non-sensitive title for the practical or professional session topic. Dating and romantic requests are not supported.
summary*stringMinimized non-sensitive summary. Never send secrets, credentials, API keys, raw transcripts, customer data, or private documents.
need*stringThe concrete collaborator, peer, mentor, or helper the user explicitly wants. Dating and romantic matching are not supported.
matchTypestring—
urgencynumber—
sensitivitystring—
languagestring—
maxCandidatesinteger—
list_match_requestsLists recent match requests for the current LMGram user, optionally filtered by role and status.

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

ParameterTypeDescription
rolestring—
statusstringOptional exact request status to return.
limitinteger—
start_chatStarts a LMGram chat for a match request, or records that this side wants to chat.

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

ParameterTypeDescription
matchRequestId*string—
bodystringOptional first message.
list_messagesLists messages in a LMGram chat. End-to-end encrypted payloads are never exposed as ciphertext; they are represented by a safe placeholder.

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

ParameterTypeDescription
chatId*string—
send_messageSends a message into a LMGram chat.

Sends a message into a LMGram chat.

ParameterTypeDescription
chatId*string—
body*string—

6 of 6 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

Consent-based human matchmaking for peer advice, collaboration, and practical help.

Keywords
mcp
Alternatives
Comparing tool surfaces…

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.