NostrPulseMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENT_NSEC | No | Alternative secret key for Nostr identity in bech32 nsec1... (alias for NOSTR_SECRET_KEY). | |
| NOSTR_SECRET_KEY | No | Secret key for Nostr identity in hex or bech32 nsec1... If not set, the server will generate or load a local keystore. | |
| NOSTRPULSE_PROFILE | No | Profile for MCP server: minimal, radar, payment, or full. Defaults to full. | full |
| AGENT_MAX_SATS_PER_TX | No | Maximum satoshis allowed per transaction. Defaults to 50. | 50 |
| AGENT_DAILY_LIMIT_SATS | No | Rolling 24-hour spending limit in satoshis. Defaults to 500. | 500 |
| AGENT_MIN_RECIPIENT_SCORE | No | Minimum required trust score (0-100) for payment recipients. Defaults to 40. | 40 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_trust_scoreA | Verify anti-Sybil Trust Score (0-100) and Web-of-Trust distance for a Nostr pubkey. |
| pay_cashu_nutzapA | Send an eCash NutZap payment (NIP-61) to a Nostr recipient under guardrail limits. |
| request_nip90_jobC | Dispatch a NIP-90 DVM analytics computation task across Nostr relays with local fallback. |
| pay_lightning_nwcC | Pay a BOLT-11 Lightning invoice via NIP-47 Nostr Wallet Connect. |
| pay_with_nwcC | Pay a BOLT-11 Lightning invoice via NIP-47 Nostr Wallet Connect (alias). |
| audit_cashu_mintB | Audit Cashu mint health, NUT-06 status, and counterparty risk score. |
| route_cashu_mintB | Route to the highest-trust, lowest-latency Cashu mint for a payment. |
| get_agent_identityA | Get the autonomous agent's Nostr public identity and npub. |
| get_spending_guardrailsA | Check current AI agent spending budget, daily limits, and remaining satoshis. |
| get_agent_telemetryB | Retrieve agent telemetry metrics, rolling spend volume, and security events. |
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 10 tools
pay_lightning_nwc and pay_with_nwc are exact aliases with identical descriptions, making them indistinguishable and creating a clear selection problem. Other tools are mostly distinct, but this duplicate payment pair is a serious coherence issue.
All tool names follow a consistent lowercase snake_case verb-first pattern, such as check_trust_score, pay_cashu_nutzap, route_cashu_mint, and get_agent_identity. Even the alias pay_with_nwc fits the same verb-first convention, so there are no mixed naming styles.
Ten tools is within the ideal range for a domain-focused server covering identity, payments, trust, mint routing, and telemetry. However, pay_with_nwc is redundant with pay_lightning_nwc, so not every tool earns its place.
The server covers core operations for Nostr identity, trust scoring, Lightning and Cashu payments, mint auditing/routing, guardrails, telemetry, and DVM job dispatch. Notable gaps include the lack of guardrail update/set operations and no obvious endpoint for fetching DVM job results or status, leaving potential dead ends.