LMGram

io.github.saezbaldoPublished by GitHub account saezbaldov0.1.2Updated Oct 24, 2026

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

The publisher's own server: Deploy to Agents

VerifiedStreamable HTTPWeb executableProductivity & WorkflowCommunication & Collaboration

Overview

AI-generated overview

LMGram is a remote MCP server for consent-based human matchmaking, letting an assistant request, chat with, and manage matches for peer advice, collaboration,or

What you can do
Read the connected LMGram profile and list recent match requests, filtered by role and status.
When to use it
Use it when the user explicitly asks to find a human collaborator, peer, mentor, or helper through LMGram, or wants to manage existing LMGram match requests and chats. It is not intended for general advice or dating.
Requirements
A remote endpoint at api.lmgram.com over streamable HTTP; no packages, environment variables, or headers are declared. It relies on the connected LMGram account, and the panel tools assume a ChatGPT conversation context.
Before you install
Match requests and intents are published to other people, and messages are sent on the user's behalf, so confirm before acting. The tools forbid including secrets, credentials, API keys, raw transcripts, customer data, or private documents. Chat payloads are end-to-end encrypted and shown as placeholders; device registration shares only a public key, and key sync is limited to the account's registered devices.

Installation

In SourceWeft

  1. Open LMGram in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.saezbaldo%2Flmgram/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "lmgram": {
      "type": "http",
      "url": "https://api.lmgram.com/mcp"
    }
  }
}

Tools

17

get_current_user

Get current LMGram profile

Returns the LMGram profile linked to the connected account.

Takes no parameters.

request_human_match

Request a 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 invoke for general advice, dating or romantic matchmaking. Never include secrets, credentials, API keys, raw transcripts, customer data, or private documents; ask for a minimized non-sensitive summary first.

ParametersneedrequiredtopicrequiredsummaryrequiredurgencylanguagematchTypesensitivitymaxCandidates

list_match_requests

List LMGram match requests

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

Parametersrolelimitstatus

start_chat

Start or request a chat

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

ParametersbodymatchRequestIdrequired

list_messages

List chat messages

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

ParameterschatIdrequired

send_message

Send a chat message

Sends a message into a LMGram chat.

ParametersbodyrequiredchatIdrequired

open_lmgram_panel

Open LMGram conversation panel

Open LMGram chats, groups and suggestions for the current ChatGPT conversation. Each conversation has a separate context; never copy a transcript or private documents. This does not publish an intent or send a message.

Takes no parameters.

panel_snapshot

Refresh conversation

Refresh this conversation's private panel data.

ParameterscontextIdrequired

panel_chat

Read private chat

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

ParametersbeforechatIdrequiredcontextIdrequired

panel_register_device

Register encryption device

Register only a public encryption key for this user's panel.

ParametersdeviceIdrequiredcontextIdrequiredpublicKeyrequired

panel_mark_read

Mark chat read

Mark the displayed chat as read.

ParameterschatIdrequiredcontextIdrequired

panel_sync_device_keys

Sync own encryption devices

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

ParameterschatIdrequiredupdatesrequiredcontextIdrequiredsourceDeviceIdrequired

panel_send_message

Send encrypted message

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

ParametersbodyrequiredchatIdrequiredcontextIdrequiredencryptedKeysrequiredsenderDeviceIdrequiredclientMessageIdrequiredencryptionNoncerequiredencryptionSchemerequired

panel_start_chat

Request conversation

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

ParameterscontextIdrequiredmatchRequestIdrequired

panel_dismiss_suggestion

Dismiss suggestion

Decline an unopened match suggestion.

ParameterscontextIdrequiredmatchRequestIdrequired

panel_join_group

Join group

Accept an existing group invitation related to this context.

ParametersroomIdrequiredcontextIdrequired

panel_create_intent

Publish approved intent

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

ParametersneedrequiredtopicrequiredsummaryrequiredlanguagecontextIdrequired

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Deploytoagents integrations

Deploy to Agents

com.deploytoagentsOfficial publisher

Remote MCP server that audits a public app's agent-facing surfaces and turns the results into a prioritized distribution plan.

Streamable HTTPWeb executable
Web Search & Scraping4 toolsOct 25, 2026