MCPVault

octagon-docs-read

MCP tool from Octagon MCP Server by OctagonAI

Reads one docs page or section as Markdown by title, URL, path, or catalog id.

How to use it

octagon-docs-read is exposed by the Octagon MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the octagon-docs-read tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Octagon MCP Server

$npx -v
FULL OCTAGON MCP SERVER LISTING

Other tools in Octagon MCP Server (25)

cache

(boolean, optional): controls agent variant routing.

captured_from

(string, optional)

captured_to

(string, optional)

conversation

(string, optional): existing Octagon conversation ID to continue a prior octagon-agent thread. Omit this on the first turn.

cursor

(string, optional)

event_ticker

(string, required)

include_analysis

(boolean, optional; when true, requests analysis columns)

includeSite

(boolean, optional): also refresh the broader https://octagonai.co/llms.txt site index.

includeSnippets

(boolean, optional): include matched snippets in results.

limit

(number, optional): maximum entries to return.

maxChars

(number, optional): maximum Markdown characters to return.

newConversation

(boolean, optional): if true, starts a fresh Octagon thread for the active session/thread anchor. Recommended for the first turn of a brand new visible chat in top-layer hosts such as Claude Desktop.

octagon-agent

Orchestrates public and private market intelligence analysis.

octagon-deep-research-agent

Performs comprehensive multi-source deep research and synthesis.

octagon-docs-list

Lists live docs sections and pages from the Octagon docs corpus.

octagon-docs-refresh

Refreshes the in-memory docs catalog from the live LLM-friendly docs endpoints.

octagon-docs-search

, octagon-docs-read, octagon-docs-list, and octagon-docs-refresh

octagon-prediction-markets-agent

for updated research reports on each prediction markets

prediction_markets_history

for structured historical market data retrieval

preferCachedContent

(boolean, optional): use the indexed docs corpus when available.

prompt

(string, required): natural language research request.

query

(string, required): search query.

section

(string, optional): filter by docs section.

source

(docs, site, or all, optional): defaults to the docs corpus.

target

(string, required): docs title, URL, path, or catalog id.