Skip to main content
Glama
ngkawaix

equity-figures-mcp

by ngkawaix
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
EQUITY_FIGURES_DATANoSet to a local folder or another base URL to read a different copy of the dataset.

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_companiesA

The companies in the dataset: ticker, name, tier, publication date, the first and last fiscal quarter held, and how many series each has.

list_metricsA

The series a ticker has: id, label, unit, kind (reported or computed), lens and latest value. search narrows the list to ids or labels containing those words (case does not matter). tier picks 'curated' or 'xbrl' for a ticker in both.

get_seriesB

One series at every quarter from start to end (fiscal labels like FY2024Q1; default the whole window). A reported point has its value, period and source (URL, document hash, locator, document and retrieval dates, accession number). A computed point names the reported figures it was computed from. A gap has its state and no value. An XBRL point lists later filings' figures for its period as revisions, and restated says whether any differs.

check_conditionA

Evaluate a measure at every quarter from start to end and test it against condition.

measure is {"name": ..., "series": ...} plus its arguments. Names: level; change (quarters, default 1); growth (quarters, default 4, in percent); vs_mean (quarters, default 4); spread (minus: a second series); ttm_sum; ttm_ratio (over: a second series, money over money, in percent). Series ids come from list_metrics. condition is a comparator and a number in the measure's unit, for example ">= 28"; the measure holds when it is true. Without a condition the values are returned with no status. A quarter that cannot be evaluated is not established, with the reason. tier picks 'curated' or 'xbrl' for a ticker in both.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored across 4 tools

Disambiguation5/5

Each tool serves a clearly distinct purpose: list_companies for discovery, list_metrics for series enumeration, get_series for raw data retrieval, and check_condition for computed evaluations. The descriptions clarify that get_series returns one series while check_condition evaluates measures and conditions, so overlap is minimal.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: list_companies, list_metrics, get_series, check_condition. The convention is predictable and easy to parse.

Tool Count5/5

With only 4 tools, the set is well-scoped for a read-only equity data server. Each tool earns its place by covering a distinct phase of the workflow: discovery, enumeration, retrieval, and conditional analysis.

Completeness5/5

The surface fully covers the domain: list_companies provides company metadata, list_metrics enumerates available series, get_series retrieves detailed point data, and check_condition supports derived measures and condition testing. No critical gaps for typical equity figure analysis.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources