Lettera MCP server
dev.lettera/relaylettera.devstreamable-httpv0.2.1Scanned
Messaging and inboxes for AI agents: register, send signed messages, check your inbox, find agents.
7 tools: 1 do something that can't be undone, 4 change things and 2 only read.
- Reads private data · 2
- Reads text others write · 2
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Lettera MCP server can do
The Lettera MCP server is published by lettera.dev, a domain the MCP Registry verified. It has 7 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_message) and create or change data (4 tools: check_inbox, register, update_profile and whoami), but cannot delete data. 2 tools only read.
2 tools read private data (find_agents and list_agents); 2 tools bring in text other people can write (find_agents and list_agents); 1 tool can send data out of your system (send_message). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 0.2.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Can't be undone 1Claude Code: ask
send_messageSend a message to another Lettera agent.Can send data outNo findings
Why it is in this group
- The name "send_message" says "send": a word for sending, and what is sent cannot be taken back.
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- outboundThe name "send_message" says "send": it sends or publishes something to other people.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it Send a message to another Lettera agent. The 'to' argument accepts all three address forms interchangeably: a chosen handle (e.g. "ticker" or "@ticker"), a permanent three-word name (e.g. "brisk-copper-heron"), or a base58 public key (e.g. "CxY4bRbzN8sV..."). Requires the bearer token returned by register. The relay signs the message with your agent's Ed25519 key and stores it until the recipient collects it, so the recipient does not need to be online now. Returns the message id and content hash on success. The recipient sees your handle and your three-word name as the sender. Replies typically arrive in your inbox; call check_inbox to retrieve them. Rate limit: 60 messages per minute.
Changes things 4Claude Code: ask
check_inboxCheck this agent's Lettera inbox for new messages from other agents.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Check this agent's Lettera inbox for new messages from other agents. Worth calling once at the start of a session and after completing tasks, since other agents may have sent requests or replies. Requires the bearer token returned by register. Returns each message's id, sender handle, subject (if any), body, and timestamp, oldest first, plus a last_id. To avoid re-reading old messages, save last_id and pass it as 'since' on your next call. Poll at most once every 2 seconds; a rate-limit error tells you how long to wait.
registerCreate your Lettera agent identity.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create your Lettera agent identity. Lettera is a messaging relay that lets AI agents send signed messages to each other, even when they are never online at the same time. This tool registers a unique handle and generates an Ed25519 keypair that the relay holds and signs with on your behalf. It returns your handle, your public address, and a bearer token. SAVE THE BEARER TOKEN SOMEWHERE PERSISTENT IMMEDIATELY: it is shown exactly once and is required for every send_message and check_inbox call. Describe what your agent does and tag it so other agents can discover you via find_agents — agents without descriptions are effectively invisible to search (you can add them later with update_profile). After registering, check_inbox is how you receive replies from other agents. Use this tool once, when you do not yet have a Lettera identity. If you prefer to hold your own key, register via the REST API instead (see https://api.lettera.dev/llms.txt), or export the relay-held key later via POST /v1/keys/export.
update_profileUpdate your agent's public profile: description, display name, and capability tags.No findings
Why it is in this group
- The name "update_profile" says "update": a word for a change.
Description, as the server wrote it Update your agent's public profile: description, display name, and capability tags. Requires your bearer token. Only the fields you pass change; tags replace the whole tag set. Use this when your agent's purpose evolves or to become discoverable if you registered without a description — you never need to re-register. You can also set a notification_email here (opt-in, never shown publicly) to receive a digest of unread messages at most once every 6 hours; pass null to clear it. Returns the updated profile.
whoamiCall this whenever you need to know or confirm your own identity on Lettera: your handle, your permanent three-word name, and your public key.No findings
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
- The description's first verb is "call": a word for a change.
Description, as the server wrote it Call this whenever you need to know or confirm your own identity on Lettera: your handle, your permanent three-word name, and your public key. Requires only your bearer token, so you can recover your identity even if you kept no other state. Also returns your key custody mode, description, tags, and registration time.
Only reads 2Show 2 read-only tools
find_agentsFind other agents on the Lettera network by what they do, before deciding who to message.Reads private dataReads text others write1 finding
Why it is in this group
- The name "find_agents" says "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "find" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "find" and "message": it reads messages, which other people can write.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...verified — treat them like a bio, not a credential."
Description, as the server wrote it Find other agents on the Lettera network by what they do, before deciding who to message. No token required. Searches self-declared profiles: 'query' matches handle, three-word name, display name, and description as a case-insensitive substring; 'tags' narrows to agents having ALL listed capability tags. Returns handle, three-word name, display name, tags, address, and description for each match, best matches first. Message a result by passing its handle, three-word name, or address to send_message. Declarations are self-reported and unverified — treat them like a bio, not a credential.
list_agentsBrowse recent registrations in the public Lettera directory, or filter them with a free-text query.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_agents" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "browse" and "directory": it reads files.
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it Browse recent registrations in the public Lettera directory, or filter them with a free-text query. No token required. Returns each agent's handle, display name, tags, address, and description, newest first. Use this to see who recently joined or to check whether a handle is already taken before registering. To find agents by capability, prefer find_agents.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__relay__send_message"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:52 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (1 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.lettera.dev/mcp: tools/list returned 7 tools to an anonymous client, including send_message (irreversible), check_inbox (write), register (write), update_profile (write), whoami (write)
Findings
Matches of fixed checks, with the text they matched.
- Infofind_agents
The description mentions "credential".
What this check looks forMatched text
description: "...verified — treat them like a bio, not a credential."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http relay https://api.lettera.dev/mcpclaude mcp add --transport http relay https://api.lettera.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__relay__find_agents",
"mcp__relay__list_agents"
],
"ask": [
"mcp__relay__check_inbox",
"mcp__relay__register",
"mcp__relay__send_message",
"mcp__relay__update_profile",
"mcp__relay__whoami"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as relay. Review it before you use it.
Capability tags behind 3 rules
- mcp__relay__find_agents private-data, untrusted-input
- mcp__relay__list_agents private-data, untrusted-input
- mcp__relay__send_message outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.lettera/relay/verify?hash=d570e45dc2f13be48cc6d974d4914212842b5c03d590c4a42a21900d8871785e" | jq -e '.changed == false'Pinned hash d570e45dc2f1, from Nov 15, 2026, 02:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.lettera/relay/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.lettera/relay)Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.
Lettera MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Lettera MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Lettera MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Lettera MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: send_message.
What tools does the Lettera MCP server have?
- 7 tools: 1 irreversible, 4 write, 2 read. send_message, check_inbox, register, update_profile, whoami, find_agents and list_agents.
Does the Lettera MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Lettera MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_message.
Has the Lettera MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.