# LMGram

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

- name: io.github.saezbaldo/lmgram
- version: 0.1.2
- connection class: R0 (autonomous)
- trust: 77/100 flags: no-repository
- quality: 90/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.saezbaldo%2Flmgram
- tools: https://api.protogrid.dev/v1/servers/io.github.saezbaldo%2Flmgram/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 45
- drivers: +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.

## Quality 90/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list carries no ttlMs, so clients re-fetch it

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 17 of 17 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,291 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 22 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 17, about 2,291 tokens to load them all
- tool set hash: 4c78fb2e8a2aed2a43d9707022a2634e
- tools last changed: 2026-09-30T20:17:58.286Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.saezbaldo/lmgram.svg)](https://protogrid.dev/servers/io.github.saezbaldo/lmgram)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-30 `panel_create_intent` changed (outputSchema)
- 2026-09-30 `panel_join_group` changed (outputSchema)
- 2026-09-30 `panel_dismiss_suggestion` changed (outputSchema)
- 2026-09-30 `panel_start_chat` changed (outputSchema)
- 2026-09-30 `panel_send_message` changed (outputSchema)
- 2026-09-30 `panel_sync_device_keys` changed (outputSchema)
- 2026-09-30 `panel_mark_read` changed (outputSchema)
- 2026-09-30 `panel_register_device` changed (outputSchema)
- 2026-09-30 `panel_chat` changed (outputSchema)
- 2026-09-30 `panel_snapshot` changed (outputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.saezbaldo%2Flmgram/changes

## Remotes

- https://api.lmgram.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (17)

- `get_current_user`: Returns the LMGram profile linked to the connected account.
- `list_match_requests`: Lists recent match requests for the current LMGram user, optionally filtered by role and status.
- `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.
- `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.
- `panel_chat`: Retrieve authorized chat data for client-side decryption, not model context.
- `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.
- `panel_dismiss_suggestion`: Decline an unopened match suggestion.
- `panel_join_group`: Accept an existing group invitation related to this context.
- `panel_mark_read`: Mark the displayed chat as read.
- `panel_register_device`: Register only a public encryption key for this user's panel.
- `panel_send_message`: Send a client-encrypted text message after the user presses Send. Retry only the identical payload and clientMessageId.
- `panel_snapshot`: Refresh this conversation's private panel data.
- `panel_start_chat`: Request a chat with a suggestion in this context, without sending a plaintext introduction.
- `panel_sync_device_keys`: Share client-encrypted message keys only with this account's registered devices. Does not send messages, plaintext or private keys.
- `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.
- `send_message`: Sends a message into a LMGram chat.
- `start_chat`: Starts a LMGram chat for a match request, or records that this side wants to chat.