Chart Library — Market-state research
Connects Claude, Cursor, VS Code, Copilot, and ChatGPT to a pattern search engine built on 25 million stock chart embeddings across 10 years of equity data. Eight tools cover pattern retrieval (search, cohort), distribution analysis (explain, analyze), regime context (context, narrative), and portfolio positioning (discover, portfolio). The cohort tool is the centerpiece: it returns empirical forward return distributions for similar historical patterns, with feature importance showing what separated winners from losers. Chain operations via cohort_id handles for sub-second refinements. You'd reach for this when building trading agents that need to answer "what happened historically when a chart looked like this" without hallucinating forecasts. Free tier gives you 200 calls per day.
- GitHub stars
- 23
- tools
- 5
- auth
- Secret needed
- transport
- STDIO, HTTP
- env var
- 1
- last updated
- Sep 10, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
market_stateCompleted-session state, historical analogs, outcome ranges, transition memory and tape for a symbol, with an optional date.
Completed-session state, historical analogs, outcome ranges, transition memory and tape for a symbol, with an optional date.
No parameter schema in public metadata yet.
daily_notePublished daily research, selection rule and settled-note tally, with an optional date.
Published daily research, selection rule and settled-note tally, with an optional date.
No parameter schema in public metadata yet.
research_qualityPublished calibration receipt, dated sample and qualifications.
Published calibration receipt, dated sample and qualifications.
No parameter schema in public metadata yet.
search_researchSearches published research and returns relevant publications, IDs, findings, sample receipts, limitations and versions.
Searches published research and returns relevant publications, IDs, findings, sample receipts, limitations and versions.
No parameter schema in public metadata yet.
read_researchReads the overview or an exact source document of a research publication, with pagination and hashes.
Reads the overview or an exact source document of a research publication, with pagination and hashes.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
CHART_LIBRARY_API_KEYsecretOptional API key. Public research works without authentication; service limits apply.
Readme
Chart Library MCP
Market memory for AI, with published research for agents and people.
Version 6.3.3 marks failed public tool calls as MCP errors while preserving their structured recovery details. Invalid requests explain how to correct the inputs; stale publication versions retain instructions to restart from the current overview. Successful response schemas and direct Python calls remain compatible.
Five read-only tools
| Tool | Input | Result |
|---|---|---|
market_state | Symbol; optional date | Completed-session state, historical analogs, outcome ranges, transition memory and tape |
daily_note | Optional date | Published daily research, selection rule and settled-note tally |
research_quality | None | Published calibration receipt, dated sample and qualifications |
search_research | Query; optional kind, limit and offset | Relevant publications, IDs, findings, sample receipts, limitations and versions |
read_research | Research ID; optional section, offset and version | Overview or an exact source document, with pagination and hashes |
Details
- Repository
- github.com/grahammccain/chart-library-mcp
- Category
- AI & LLM Tools
- Package
chartlibrary-mcp- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Unleash Mcpunleash/unleash-mcpMCP server for Unleash: an AI-agent-friendly interface to Unleash21stars
Codex Mcp Toolx51xxx/codex-mcp-toolMCP server bridging AI assistants to OpenAI Codex CLI for code analysis and review21stars
hmem — Humanlike Memory for AI Agentsbumblebiber/hmemPersistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.20stars
Kirbah Mcp Youtubekirbah/mcp-youtubeProvide token-optimized, structured YouTube data to enhance your LLM applications. Access efficien…19stars
NeuroDock Cognitive Graphtlennon-ie/neurodockA local typed-edge graph of people, projects, and decisions that externalises memory.18stars
Mcp As A Judgeothervibes/mcp-as-a-judgeMCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations17stars