_ registry / mcp streamable-http · checked 1h ago

LMGram

https://api.lmgram.com

Registry code: f82c8f29f9827ca0

api record

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

from a public catalogue that lists it, not from the operator

endpoint
https://api.lmgram.com/mcp
protocol
streamable-http ·2025-03-26
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is LMGram live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is LMGram free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does LMGram have?
17 tools: panel_chat, panel_snapshot, open_lmgram_panel, get_current_user, panel_dismiss_suggestion, request_human_match, panel_sync_device_keys, panel_send_message, ….
Is LMGram safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 99.5%· all time 99.5%

latency
379ms

last good check

priced tools
0

of 17 tools

_ answered our checks, 90 days 370 checks · signed record
  • down → live
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
communication chat & messaging
used for
  • request a match with a human for advice
  • chat with matched people
  • join group conversations
  • list match requests
takes → gives
text → data, text
tools
6 reads7 changes data4 sends messages
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 17 tools
14 auth-required 3 never probed 14 of 17 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • get_current_user reads auth-required 7h ago

    Returns the LMGram profile linked to the connected account.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • panel_dismiss_suggestion changes data auth-required never probed

    Decline an unopened match suggestion.

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "matchRequestId"
  ],
  "properties": {
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    },
    "matchRequestId": {
      "type": "string",
      "maxLength": 32
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • request_human_match changes data auth-required never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "topic",
    "summary",
    "need"
  ],
  "properties": {
    "need": {
      "type": "string",
      "description": "The concrete collaborator, peer, mentor, or helper the user explicitly wants. Dating and romantic matching are not supported."
    },
    "topic": {
      "type": "string",
      "description": "Short, non-sensitive title for the practical or professional session topic. Dating and romantic requests are not supported."
    },
    "summary": {
      "type": "string",
      "description": "Minimized non-sensitive summary. Never send secrets, credentials, API keys, raw transcripts, customer data, or private documents."
    },
    "urgency": {
      "type": "number",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0
    },
    "language": {
      "type": "string"
    },
    "matchType": {
      "enum": [
        "peer",
        "mentor",
        "collaborator",
        "helper"
      ],
      "type": "string",
      "default": "peer"
    },
    "sensitivity": {
      "enum": [
        "normal",
        "sensitive",
        "high"
      ],
      "type": "string",
      "default": "normal"
    },
    "maxCandidates": {
      "type": "integer",
      "default": 5,
      "maximum": 20,
      "minimum": 1
    }
  },
  "additionalProperties": false
}
    arguments 57 lines
  • panel_sync_device_keys changes data auth-required never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "chatId",
    "sourceDeviceId",
    "updates"
  ],
  "properties": {
    "chatId": {
      "type": "string",
      "maxLength": 32
    },
    "updates": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "messageId",
          "encryptionNonce",
          "encryptedKeys"
        ],
        "properties": {
          "messageId": {
            "type": "string",
            "maxLength": 32
          },
          "encryptedKeys": {
            "type": "object",
            "maxProperties": 100,
            "additionalProperties": {
              "type": "string",
              "maxLength": 96
            }
          },
          "encryptionNonce": {
            "type": "string",
            "maxLength": 40
          }
        },
        "additionalProperties": false
      },
      "maxItems": 60,
      "minItems": 1
    },
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    },
    "sourceDeviceId": {
      "type": "string",
      "maxLength": 32
    }
  },
  "additionalProperties": false
}
    arguments 57 lines
  • panel_send_message sends messages auth-required never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "chatId",
    "clientMessageId",
    "body",
    "encryptionScheme",
    "encryptionNonce",
    "senderDeviceId",
    "encryptedKeys"
  ],
  "properties": {
    "body": {
      "type": "string",
      "maxLength": 32000
    },
    "chatId": {
      "type": "string",
      "maxLength": 32
    },
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    },
    "encryptedKeys": {
      "type": "object",
      "maxProperties": 1000,
      "additionalProperties": {
        "type": "string",
        "maxLength": 96
      }
    },
    "senderDeviceId": {
      "type": "string",
      "maxLength": 32
    },
    "clientMessageId": {
      "type": "string",
      "maxLength": 36
    },
    "encryptionNonce": {
      "type": "string",
      "maxLength": 40
    },
    "encryptionScheme": {
      "type": "string",
      "maxLength": 32
    }
  },
  "additionalProperties": false
}
    arguments 53 lines
  • panel_register_device changes data auth-required never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "deviceId",
    "publicKey"
  ],
  "properties": {
    "deviceId": {
      "type": "string",
      "maxLength": 32
    },
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    },
    "publicKey": {
      "type": "string",
      "maxLength": 64
    }
  },
  "additionalProperties": false
}
    arguments 24 lines
  • start_chat sends messages auth-required never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "matchRequestId"
  ],
  "properties": {
    "body": {
      "type": "string",
      "description": "Optional first message."
    },
    "matchRequestId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 16 lines
  • send_message sends messages auth-required never probed

    Sends a message into a LMGram chat.

    mcp-tool

    {
  "type": "object",
  "required": [
    "chatId",
    "body"
  ],
  "properties": {
    "body": {
      "type": "string"
    },
    "chatId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 16 lines
  • list_messages reads auth-required 24h ago

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "chatId"
  ],
  "properties": {
    "chatId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 12 lines
  • panel_mark_read changes data auth-required never probed

    Mark the displayed chat as read.

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "chatId"
  ],
  "properties": {
    "chatId": {
      "type": "string",
      "maxLength": 32
    },
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • panel_start_chat sends messages auth-required never probed

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "matchRequestId"
  ],
  "properties": {
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    },
    "matchRequestId": {
      "type": "string",
      "maxLength": 32
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • panel_join_group changes data auth-required never probed

    Accept an existing group invitation related to this context.

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "roomId"
  ],
  "properties": {
    "roomId": {
      "type": "string",
      "maxLength": 32
    },
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • panel_create_intent changes data auth-required never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "topic",
    "summary",
    "need"
  ],
  "properties": {
    "need": {
      "type": "string",
      "maxLength": 1000
    },
    "topic": {
      "type": "string",
      "maxLength": 240
    },
    "summary": {
      "type": "string",
      "maxLength": 2000
    },
    "language": {
      "type": "string",
      "maxLength": 40
    },
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    }
  },
  "additionalProperties": false
}
    arguments 33 lines
  • list_match_requests reads auth-required 7h ago

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

    mcp-tool

    {
  "type": "object",
  "properties": {
    "role": {
      "enum": [
        "candidate",
        "requester"
      ],
      "type": "string",
      "default": "candidate"
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "status": {
      "enum": [
        "pending",
        "chat_requested",
        "accepted",
        "declined"
      ],
      "type": "string",
      "description": "Optional exact request status to return."
    }
  },
  "additionalProperties": false
}
    arguments 30 lines
  • panel_chat reads unknown 24h ago

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

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId",
    "chatId"
  ],
  "properties": {
    "before": {
      "type": "string",
      "maxLength": 32
    },
    "chatId": {
      "type": "string",
      "maxLength": 32
    },
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    }
  },
  "additionalProperties": false
}
    arguments 23 lines
  • panel_snapshot reads unknown 24h ago

    Refresh this conversation's private panel data.

    mcp-tool

    {
  "type": "object",
  "required": [
    "contextId"
  ],
  "properties": {
    "contextId": {
      "type": "string",
      "maxLength": 43,
      "minLength": 43
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • open_lmgram_panel reads unknown 7h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {},
  "additionalProperties": false
}
    arguments 6 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id f82c8f29f9827ca0.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/f82c8f29f9827ca0/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/f82c8f29f9827ca0/badge.svg)](https://brick.blue/agent/f82c8f29f9827ca0?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.