withcoral / coral
One SQL interface over APIs, files, and live sources — built for agents.
github.com/withcoral/coralIndexed at f6fc6e0Up to date with upstream
What is coral?
coral is a local-first SQL runtime for agents that queries APIs, files, and other data sources through one interface. Agents can inspect schemas, run SQL, and use the same runtime over MCP. coral is written primarily in Rust.
Written by a model from the README and the source
Code health
Health scores land with the first index: complexity, duplication, coverage, churn and ownership across every file.
Use withcoral/coral in your agent
Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.
- 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
- 2.Paste the server URL below as the Remote MCP server URL, then click Add.
- 3.Click Connect. A Repowise sign-in window opens. Approve access.
- 4.Repowise's tools are now available in your Claude chats.
Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.
Docshttps://api.repowise.dev/mcp/withcoral/coral
This repo is public, so anyone with a Repowise account and an API key can connect.
Try asking
- get_overview()
- get_answer("how is coral put together?")
- get_why("why is coral structured this way?")
Explore coral
- DocumentationModule-by-module documentation, written from the source.
- ArchitectureDependency graph, layers and third-party dependencies.
- Code healthEvery file's score and the findings behind it.
- CommitsEach commit's effect on code health.
- OverviewEverything else the index found: contributors, decisions, what changed this week.
Key features of coral
- coral provides one SQL interface for querying multiple live APIs and local files.
- coral exposes the same query runtime over MCP for agent use.
- coral supports local joins across tables from different sources.
- coral handles pagination and returns tabular rows for read tasks.
- coral supports bundled sources such as Datadog, GitHub, Linear, Sentry, Stripe, JSONL files, and Parquet files.
How withcoral/coral works
Agents enter through the coral CLI or the built-in MCP server, where SQL queries target tables exposed by configured sources. Source specifications define how APIs or local datasets are reached and which tables and columns they provide. The sources directory holds source integrations, while crates contains the Rust implementation of the runtime and related components. coral translates SQL into API calls or file reads, fetches data, and returns one result set. Joins across sources are executed locally after each source provides its data. Local configuration stores installed-source metadata, variables, source specifications, and secrets.
Getting started with coral
- Install coral on macOS.
brew install withcoral/tap/coral - Discover bundled sources.
coral source discover - Add GitHub interactively.
coral source add --interactive github - Query available tables.
coral sql "SELECT schema_name, table_name FROM coral.tables ORDER BY 1, 2"
Commands copied from the README
withcoral/coral FAQ
What is coral?
coral is a local-first SQL runtime for agents. coral provides one interface for querying APIs, files, and other data sources.
How does coral work?
coral translates SQL into API calls or file reads and returns one result set. coral exposes configured sources as SQL schemas and performs cross-source joins locally.
How do I install coral?
coral can be installed on macOS with brew install withcoral/tap/coral. coral can also be installed on Linux with the install command shown in its quickstart.
What language is coral written in?
coral is written primarily in Rust.
How is the coral code organized?
coral organizes its implementation mainly under crates, with source integrations under sources, documentation under docs, and interface files under ui. The xtask and plugins directories provide additional project components.
Who is coral for?
coral is for agents and people who need to query APIs, files, and other data sources with SQL. coral supports agent access through its built-in MCP server.
What license does coral use?
coral uses the Apache-2.0 license.
The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.
About this page
Get a page like this for your own codebase
Repowise built this map of withcoral/coral from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.
Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.
Maintain withcoral/coral?
Claim this page, add a badge to the README, or re-index it.
Claim this page
Sign in with GitHub and we check that you are an admin or maintainer of withcoral/coral. Then add a badge to the README that links readers here.
Add a badge to your README
Every badge is public, cached, and updates on its own after every index. Nothing to install.
Repowise badge
Links to this page, with no score on it. Adding it also re-indexes the repo every week.
[](https://repowise.dev/repo/withcoral/coral?src=badge_wiki)Code health badge
The repo's health score out of 10, from the latest index.
[](https://repowise.dev/repo/withcoral/coral?src=badge_health)Code health card
A larger card with the score, its change since the last index, and when it was measured. The HTML version follows the reader's light or dark theme.
[](https://repowise.dev/repo/withcoral/coral?src=badge_card)