inbox-recall
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | Yes | PostgreSQL connection string for the messages database, e.g. postgresql://sync:sync@localhost:5432/messages. | |
| RECALL_TOKEN | No | Bearer token required when connecting to the MCP endpoint over Streamable HTTP. | |
| EMBED_PROVIDER | No | Embedding provider to use, such as hash, ollama, openai, or lmstudio. | |
| EMBED_QUERY_PREFIX | No | Prefix prepended to search queries before embedding, e.g. "search_query: " for nomic-embed-text. | |
| EMBED_DOCUMENT_PREFIX | No | Prefix prepended to documents before embedding, e.g. "search_document: " for nomic-embed-text. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
These tools search the user's own message history: every chat synced from Beeper (WhatsApp, Signal, Telegram, iMessage, Discord, Instagram and more) plus Instagram DMs from the browser extension, in one Postgres archive.
How to use them well:
Start with search_messages. Put the topic in
queryand move people, chats, networks and dates into filters: "what did Maya say about the lease last spring" becomes query="lease", sender=["Maya"], when="last spring".senderis who wrote the message ("me" = the user).personlimits to conversations that include someone.whentakes plain English ("last spring", "march 2024", "past 2 weeks").Results are conversation excerpts. Lines marked → are matches; the rest is context. Use get_conversation(message_id=...) to read more of a thread.
Use find_people or list_conversations when a name or chat is ambiguous.
Always cite the messages you rely on by id, like [#4812], with sender and date.
Leave
queryempty to list every message matching the filters, newest first.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_messagesA | Hybrid semantic + keyword + fuzzy search across every synced chat and network. Returns ranked matches as conversation excerpts with surrounding messages, each line tagged with a citable message id. Filter by sender, person, chat, network, direction and time ( |
| get_conversationA | Reconstruct a thread. Pass message_id to read the messages around it (before/after counts), conversation_id with |
| get_messagesB | Fetch specific messages by id (to verify a citation), optionally with context. |
| list_conversationsA | List chats, most recently active first, with message counts, date span and the people in them. Filter by title, network, a person in the chat, or activity in a time range. |
| find_peopleA | Look up people by name or handle across every network. One person on WhatsApp and Instagram shows up once, with message counts per network. Use it to resolve who someone is before filtering. |
| archive_statsC | Networks, message counts, date coverage and embedding coverage of the archive. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Most tools have clearly distinct roles: find_people resolves identities, archive_stats reports coverage, search_messages discovers messages, list_conversations browses chats, and get_conversation reconstructs threads. There is some overlap between get_conversation around a message_id and get_messages with optional context, but descriptions largely disambiguate.
Tool names are consistently snake_case and mostly follow an action_object pattern (find_people, search_messages, get_conversation, get_messages, list_conversations). archive_stats is the only clear deviation because it is noun-first rather than verb-first.
Six tools are well-scoped for a read-only message archive. Each tool covers a distinct retrieval need: identity resolution, statistics, search, conversation reconstruction, message verification, and chat listing.
The surface covers the core read-only lifecycle: discover people, inspect archive coverage, search messages, list conversations, reconstruct threads, and verify specific message citations. No obvious lifecycle gaps for an archive-recall server.