Opencode Palantir

opencode-palantir

[](https://www.npmjs.com/package/@openontology/opencode-palantir) [](https://www.npmjs.com/package/@openontology/opencode-palantir)

OpenCode plugin that provides:

• Palantir public documentation tools backed by a local Parquet database
• Foundry MCP bootstrapping helpers (commands, agents, and optional auto-bootstrap)

NPM package: https://www.npmjs.com/package/@openontology/opencode-palantir

Supported OS

• Supported: macOS, Linux
• Windows: not supported (WSL2 might work, but we don’t debug Windows-specific issues)

Install (OpenCode)

Add the plugin in your OpenCode config (opencode.jsonc):

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["@openontology/opencode-palantir@^0.1.4"]
}

Restart OpenCode.

After enabling the plugin, OpenCode will automatically register:

• Tools: get_doc_page, list_all_docs
• Commands: /refresh-docs, /refresh-docs-rescrape, /setup-palantir-mcp, /rescan-palantir-mcp-tools
• Agents: foundry-librarian, foundry

Versions: how to get the latest

Prefer pinned or semver range installs (like @^0.1.4), and update intentionally.

Avoid using @latest in config:

• it can make startup slower (npm resolution/install on startup)
• it makes behavior less deterministic
• depending on caching, you may not get the upgrade behavior you expect

To find the newest version and changelog:

• NPM versions: https://www.npmjs.com/package/@openontology/opencode-palantir
• GitHub releases: https://github.com/anandpant/opencode-palantir/releases
• Repo changelog: CHANGELOG.md

(Optional) Install per-project

In your project repo, add the plugin as a dependency inside .opencode/ (keeps plugin deps separate from your app deps):

mkdir -p .opencode

cat > .opencode/package.json  .opencode/plugins/opencode-palantir.js ', '--foundry-api-url', foundryUrl], { stdio: 'inherit' }); child.on('exit', (code) => process.exit(code ?? 1));"
      ],
      "environment": {
        "FOUNDRY_URL": "{env:FOUNDRY_URL}",
        "FOUNDRY_TOKEN": "{env:FOUNDRY_TOKEN}"
      }
    }
  }
}

Development (this repo)

Setup

mise run setup

Common tasks

• Build: mise run build
• Test: mise run test
• Lint: mise run lint
• Typecheck: mise run typecheck
• Format: mise run format

Smoke test the built artifact

mise run smoke

Fetch docs parquet (local dev)

Fetch all Palantir docs into data/docs.parquet (~2 minutes, ~17MB file):

bun run src/docs/fetch-cli.ts

Parquet schema (local dev)

The Parquet file contains a single row group with the following columns:

| Column | Type | Description | | ------------ | ------- | ----------------------------------- | | url | string | Page URL path (e.g. /foundry/...) | | title | string | Page title | | content | string | Full page content (Markdown) | | word_count | integer | Word count of content | | meta | string | JSON-encoded metadata | | fetched_at | string | ISO 8601 timestamp of when fetched |

Example (Bun):

import { parquetReadObjects } from 'hyparquet';

const file = await Bun.file('data/docs.parquet').arrayBuffer();

// List all pages (url + title only)
const pages = await parquetReadObjects({ file, columns: ['url', 'title'] });
console.log(`${pages.length} pages`);

Release notes

For maintainers, see RELEASING.md.

Author

Anand Pant

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: anandpant
• Source: anandpant/opencode-palantir
• License: MIT
• Homepage: https://www.npmjs.com/package/@openontology/opencode-palantir

Install and usage instructions live in the source repository linked above.