# Grahammccain Chart Library MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.grahammccain%2Fchart-library
Registry id: `mcp-registry/io.github.grahammccain/chart-library`
Status: live (checked 2026-10-26T20:17:33.303Z)

## Measurements (30 days)

- Uptime: 99.6%
- Checks: 4799
- Outages (90 days): 7

## Install

```json
{
  "mcpServers": {
    "grahammccain-chart-library-mcp-server": {
      "type": "http",
      "url": "https://chartlibrary.io/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http grahammccain-chart-library-mcp-server https://chartlibrary.io/mcp
```

## Tools (21)

- `check_company_forecasts`: Compare frozen revenue forecasts with reported results. Forecasts must precede quarter end. Missing results and definition mismatches remain unavailable. This i
- `cohort_groupby`: Split the cohort by a contextual feature and compare distributions.
- `cohort_introspect`: Analyze the cohort's forward-return distribution and feature importance.
- `compare_company_history`: Two to six companies, one quarter end (YYYY-MM-DD), USD history and provenance. Mismatched source concepts or missing history never become comparable numerical 
- `compare_company_revisions`: Compare facts, assumptions, scenarios and thesis between immutable revisions. Omit to_revision for latest.
- `context`: Get current market context, sector rotation, and regime.
- `daily_note`: Read the published daily research, its selection rule and settled-note tally in one call. No arguments needed. Optional date (YYYY-MM-DD) selects a published se
- `explain`: Generate a natural language explanation of the cohort's implications.
- `get_company_file`: One covered company's living research file (company_file.v1): business, three drivers, the last eight fiscal quarters from SEC XBRL with provenance on every num
- `get_company_revisions`: Browse immutable published versions, reasons and pinned JSON/CSV links. Follow next_offset.
- `get_company_status`: Current monitoring alongside the immutable company file. Preserve scan versus review clocks, pending discovery leads, source failures and limitations. Never use
- `get_company_watchlist`: Latest model revisions, current review status and qualified checkpoints for 1-20 companies. No list is saved on the server. Compare revisions with your own last
- `list_coverage`: The research hub's coverage universe: clusters and symbols, with each symbol's company-file revision, as_of date, whether a compiled file exists, and skeleton=t
- `market_state`: One call: completed-session state, tape, historical analogs, outcome ranges and transition memory. symbol is a stock ticker; optional date is YYYY-MM-DD. Omit d
- `morning_issue`: Chart Library's morning issue: the three most talked-about US stocks gapping before the open, each with today's chart, three plain bullets (where it came from, 
- `pull_comps`: Get the cohort of historical analogs for a given symbol, date, and timeframe.
- `read_research`: Read a publication ID returned by search_research, preserving its evidence. source_fields returns exact catalog status/receipt fields; content.source_rows expos
- `research_quality`: Read the published five-session calibration receipt; no arguments or earlier tool call needed. Preserve the receipt's dates, sample sizes and qualifications. Co
- `run_company_scenario`: Calculate a temporary scenario from 1-20 assumption cell IDs and numerical values in their published units. Read get_company_file first. Reported facts, guidanc
- `search`: Search for chart patterns by symbol, date, or query; returns a cohort_id for further analysis.
- `search_research`: Find published studies, Casebook and agent protocols by keyword. kind: all, study, casebook or agent_protocol. limit 1-20; use next_offset for more results. Ret

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.