protogrid

Search / io.github.saezbaldo/lmgram

LMGram

R0· no sign-in

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

v0.1.2 · active · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality90strong
Trust77of 100
Uptime, 30 days100%
Latency p50157 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "lmgram": {
      "type": "http",
      "url": "https://api.lmgram.com/mcp"
    }
  }
}
claude mcp add --transport http lmgram https://api.lmgram.com/mcp
[mcp_servers.lmgram]
url = "https://api.lmgram.com/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lmgram": {
      "type": "remote",
      "url": "https://api.lmgram.com/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "lmgram": {
      "type": "http",
      "url": "https://api.lmgram.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=lmgram&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLmxtZ3JhbS5jb20vbWNwIn0%3D"
}
{
  "servers": {
    "lmgram": {
      "type": "http",
      "url": "https://api.lmgram.com/mcp"
    }
  }
}
{
  "mcpServers": {
    "lmgram": {
      "httpUrl": "https://api.lmgram.com/mcp"
    }
  }
}
extensions:
  "lmgram":
    enabled: true
    name: "lmgram"
    type: streamable_http
    uri: "https://api.lmgram.com/mcp"
    timeout: 300

Quality 90 / 100strong

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list carries no ttlMs, so clients re-fetch it
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene100 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations17 of 17 tools declare readOnlyHint or destructiveHint
  • pass
    tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
  • pass
    tools.token_costabout 2,291 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability75 · weight 15
  • warn
    stability.changes22 tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

17 tools, about 2,291 tokens to load them all · tool set 4c78fb2e8a2a · tools last changed 2026-09-30 · checked 2026-10-20 10:35 UTC

Tool changes

  • panel_create_intentchangedoutput schema
  • panel_join_groupchangedoutput schema
  • panel_dismiss_suggestionchangedoutput schema
  • panel_start_chatchangedoutput schema
  • panel_send_messagechangedoutput schema
  • panel_sync_device_keyschangedoutput schema
  • panel_mark_readchangedoutput schema
  • panel_register_devicechangedoutput schema
  • panel_chatchangedoutput schema
  • panel_snapshotchangedoutput schema

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 77 / 100

no-repository
provenance45
liveness100
freshness85
hygiene80

+website +reachable +uptime-100% ~updated-90d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://api.lmgram.com/mcp streamable-httpnoneyes100%157 ms2026-07-282026-10-20

Tools (17)

get_current_userread-onlyReturns the LMGram profile linked to the connected account.
list_match_requestsread-onlyLists recent match requests for the current LMGram user, optionally filtered by role and status.
list_messagesread-onlyLists messages in a LMGram chat. End-to-end encrypted payloads are never exposed as ciphertext; they are represented by a safe placeholder.
open_lmgram_panelread-onlyOpen 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.
panel_chatread-onlyRetrieve authorized chat data for client-side decryption, not model context.
panel_create_intentPublish only the minimized intent explicitly reviewed and submitted by the user in this conversation panel. Do not include secrets, private transcripts, or dating requests.
panel_dismiss_suggestiondestructiveDecline an unopened match suggestion.
panel_join_groupAccept an existing group invitation related to this context.
panel_mark_readMark the displayed chat as read.
panel_register_deviceRegister only a public encryption key for this user's panel.
panel_send_messageSend a client-encrypted text message after the user presses Send. Retry only the identical payload and clientMessageId.
panel_snapshotread-onlyRefresh this conversation's private panel data.
panel_start_chatRequest a chat with a suggestion in this context, without sending a plaintext introduction.
panel_sync_device_keysShare client-encrypted message keys only with this account's registered devices. Does not send messages, plaintext or private keys.
request_human_matchCreates 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.
send_messageSends a message into a LMGram chat.
start_chatStarts a LMGram chat for a match request, or records that this side wants to chat.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.saezbaldo/lmgram",
  "title": "LMGram",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.lmgram.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.2",
  "websiteUrl": "https://lmgram.com",
  "description": "Consent-based human matchmaking for peer advice, collaboration, and practical help."
}