Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SIGRANK_API_BASENoOverrides the board host for the SigRank API.https://signalaf.com

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
rank_pasteA

Rank a paste of ccusage-style token counts. Accepts JSON {input,output,cacheCreate,cacheRead} or 4 whitespace-separated numbers in that order. Returns Υ Yield, SNR, Leverage, Velocity, 10xDEV, class, AND a deterministic prose "card". Token-only; computes locally.

get_leaderboardA

The live public SigRank board (signalaf.com) — operators ranked by yield.

get_operatorC

One operator's live profile by codename.

submit_pasteA

Rank a paste AND publish it to the live SigRank board in one call. Computes the cascade locally (instant preview + card), then submits the RAW paste to the board's web-paste endpoint, which re-parses and re-scores it server-side (authoritative). A codename is required to publish; omit it for a local preview only. Token-only, no auth (matches the web paste path). Best with a ccusage JSON paste — the 4-number form ranks locally but the board may reject it.

tokenpullA

Pull your LOCAL token usage from the platform's session logs and rank it across the four windows (7d/30d/90d/all-time) with the cascade — zero paste. Token-only: reads usage counts not message content. The numbers stay on your machine unless you submit them. Some platforms may have partial data (estimated=true when cacheCreate isn't available) or a dataGap note when the log format doesn't expose raw token counts.

tokenpull_submitA

Pull your LOCAL usage (tokenpull) AND publish it to the SigRank board in one call — the zero-paste flow. Submits the canonical 4 pillars per window, each re-scored server-side and tagged with the source platform. Requires a codename to publish; omit for local preview. Token-only.

rank_windowsA

Rank all four time windows (7d/30d/90d/all-time) in one call from a dashboard paste — paste the full table from ccusage, tokscale, or the Claude Max usage dashboard and get the cascade (Υ, SNR, Leverage, Velocity, 10xDEV, class, card) for each window. Each window is parsed and scored independently. Named keys required (input/output/cacheCreate/cacheRead); positional order is NOT safe here (dashboards list cache_read before cache_create — see WINDOWED_PROFILES gotcha). Omit windows you don't have — partial input is allowed (1–4 windows). Does NOT submit to the board; use tokenpull_submit for zero-paste publishing.

watch_tokenpullA

Watch your local token logs and re-derive your cascade whenever new sessions are written — a live tune meter. Polls at a configurable interval (default 60s), diffs against the last snapshot, and returns the updated cascade when something changes. The push-to-board step is TODO(AUTH.WIRE) — currently returns the diff locally so you can see your score move in real time without submitting.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SunrisesIllNeverSee/sigrank-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server