dm-read
Read direct messages addressed to the active identity. Decrypts both NIP-17 (gift wrap) and NIP-04 (legacy). Each message includes { from, content, protocol, decrypted }. Gracefully handles decryption failures without crashing.
This record as markdown: /tools/dev-forgesworn-bray/dm-read.md
What dm-read does on Nostr Bray
AI agents call dm-read to retrieve information from Nostr Bray without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why dm-read is rated Low
This tool retrieves and decrypts existing direct messages without creating, modifying, or deleting any data. It has no side effects beyond reading. While it handles sensitive encrypted communication, the read-only nature and focus on the active user's own messages (not third-party data manipulation) keeps this in the Read category with low severity.
From the tool's definition Tool description explicitly states 'Read direct messages' and 'Decrypts', which are retrieval operations with no modification capability. The tool only accesses existing messages addressed to the active identity and returns their content.
Attacks that exploit this kind of access
The rule that runs dm-read safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nostr Bray, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For dm-read, this is the rule to start with:
dm-read is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nostr Bray, apply this rule, and every dm-read call is checked against it from then on.
Questions about dm-read
Read direct messages addressed to the active identity. Decrypts both NIP-17 (gift wrap) and NIP-04 (legacy). Each message includes { from, content, protocol, decrypted }. Gracefully handles decryption failures without crashing. It is categorised as a Read tool in the Nostr Bray MCP Server, which means it retrieves data without modifying state.
Register the Nostr Bray MCP server in PolicyLayer and add a rule for dm-read: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nostr Bray. Nothing to install.
dm-read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the dm-read rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for dm-read. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
dm-read is provided by the Nostr Bray MCP server (nostr-bray). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nostr Bray, and thousands of servers like it.
This server
Across the catalogue