Maximum Sats MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| ask_bitcoinA | Ask a question about Bitcoin, Lightning Network, or cryptocurrency. Powered by Llama 3.3 70B. Costs 21 sats via Lightning L402. |
| generate_imageA | Generate an image from a text prompt using FLUX.1 Schnell (12B). Costs 100 sats via Lightning L402. |
| wot_scoreA | Look up a Nostr pubkey's Web of Trust score (PageRank-based, 0-100). Returns score, rank, percentile, followers. 50 free requests/day, then L402. |
| wot_sybil_checkA | Run 5-signal Sybil detection on a Nostr pubkey. Analyzes follower quality, mutual trust ratio, follow diversity, temporal patterns, and community integration. Returns classification: genuine, likely_genuine, suspicious, or likely_sybil. |
| wot_trust_pathA | Find the trust path between two Nostr pubkeys. Shows hop-by-hop path with trust scores at each hop. Useful for 'how am I connected to this person?' |
| wot_network_healthA | Get Nostr network health metrics: node count, edge count, Gini coefficient (decentralization), power-law exponent, density, and component analysis. No pubkey needed. |
| wot_follow_qualityA | Analyze the quality of a Nostr pubkey's follow list. Returns quality score, ghost follower ratio, diversity entropy, and improvement suggestions. |
| wot_trust_circleA | Get a pubkey's trust circle (mutual follows with trust strength). Returns members with roles, cohesion, and density metrics. |
| wot_anomaliesA | Detect anomalous patterns in a Nostr pubkey's network behavior. Checks for ghost followers, asymmetric relationships, cluster patterns, and suspicious activity. |
| wot_predict_linkA | Predict how likely two Nostr pubkeys are to connect. Uses 5 topology signals: Common Neighbors, Adamic-Adar, Preferential Attachment, Jaccard, WoT Proximity. |
| wot_compare_providersB | Compare trust scores for a pubkey across multiple NIP-85 providers. Shows consensus classification and provider agreement. |
| wot_influenceA | Simulate what happens if one pubkey follows/unfollows another. Shows ripple effect across the network using differential PageRank. |
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 12 tools
The tools are mostly distinct with clear purposes, but there is some overlap in the Web of Trust (WoT) analysis tools. For example, wot_anomalies and wot_sybil_check both detect suspicious activity, which could cause confusion. However, each tool's description helps differentiate them by focusing on specific aspects like network patterns versus Sybil detection signals.
The naming follows a highly consistent pattern. All Web of Trust tools use the 'wot_' prefix followed by a descriptive action or concept (e.g., wot_score, wot_trust_path). The non-WoT tools (ask_bitcoin, generate_image) also use clear verb_noun or action_object formats, maintaining overall consistency without mixing conventions.
With 12 tools, the count is well-scoped for the server's purpose of providing Bitcoin/Lightning and Nostr Web of Trust services. It covers a broad range of functionalities without being overwhelming, with 2 tools for general Bitcoin tasks and 10 dedicated to WoT analysis, each serving a distinct role in the ecosystem.
The tool set offers comprehensive coverage for Nostr Web of Trust analysis, including scoring, network health, trust paths, and anomaly detection. Minor gaps exist, such as no direct tools for modifying or managing trust relationships (e.g., follow/unfollow actions), but agents can likely work around this given the strong analytical focus.