LMGram
Consent-based human matchmaking for peer advice, collaboration, and practical help.
| Endpoint | https://api.lmgram.com/mcp (streamable-http) |
|---|---|
| Registry version | 0.1.2 |
| Now | 17 tools · grade B (85) · pin ts_65c136469e9b249205f68330eb8f2ebc · protocol 2025-03-26 |
| First / last listed | 2026-10-30 02:19 UTC / 2026-10-30 02:19 UTC |
| Grade over time | 2026-10-30: B (85), 17 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: get_current_user request_human_match list_match_requests start_chat list_messages send_message open_lmgram_panel panel_snapshot panel_chat panel_register_device panel_mark_read panel_sync_device_keys panel_send_message panel_start_chat panel_dismiss_suggestion panel_join_group panel_create_intent
get_current_user | Returns the LMGram profile linked to the connected account. params: none |
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 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. params: topic*, summary*, need*, matchType, urgency, sensitivity, language, maxCandidates |
list_match_requests | Lists recent match requests for the current LMGram user, optionally filtered by role and status. params: role, status, limit |
start_chat | Starts a LMGram chat for a match request, or records that this side wants to chat. params: matchRequestId*, body |
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. params: chatId* |
send_message | Sends a message into a LMGram chat. params: chatId*, body* |
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 private documents. This does not publish an intent or send a message. params: none |
panel_snapshot | Refresh this conversation's private panel data. params: contextId* |
panel_chat | Retrieve authorized chat data for client-side decryption, not model context. params: contextId*, chatId*, before |
panel_register_device | Register only a public encryption key for this user's panel. params: contextId*, deviceId*, publicKey* |
panel_mark_read | Mark the displayed chat as read. params: contextId*, chatId* |
panel_sync_device_keys | Share client-encrypted message keys only with this account's registered devices. Does not send messages, plaintext or private keys. params: contextId*, chatId*, sourceDeviceId*, updates* |
panel_send_message | Send a client-encrypted text message after the user presses Send. Retry only the identical payload and clientMessageId. params: contextId*, chatId*, clientMessageId*, body*, encryptionScheme*, encryptionNonce*, senderDeviceId*, encryptedKeys* |
panel_start_chat | Request a chat with a suggestion in this context, without sending a plaintext introduction. params: contextId*, matchRequestId* |
panel_dismiss_suggestion | Decline an unopened match suggestion. params: contextId*, matchRequestId* |
panel_join_group | Accept an existing group invitation related to this context. params: contextId*, roomId* |
panel_create_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. params: contextId*, topic*, summary*, need*, language |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.