mcpolyglot
One MCP server for the databases and REST APIs you already have (Postgres, MySQL, SQLite, MongoDB, OpenAPI), with per-table policy, read-only enforcement, redaction and audit
What XERJ indexed
Snapshot
The whole repository at commit 03059f1e73 (2026-09-28). develop is 25 commits ahead.
Selected work

“Harden SQL classifier: whole-row refs, server-access functions, INTO,…”. 8 files, 382 lines in packages/connector-sql, packages/cli.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-27. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
ai-agentsanthropicclaudellmmcpmodel-context-protocolmongodbmysql
Example questions
- How does mcpolyglot implement ai-agents?
- What does packages/connector-sql do in mcpolyglot?
- Show the anthropic code in mcpolyglot.
Inside the indexed corpus
- 170 files, 574.0 KB in total, about 3.4 KB per file.
- The selected commit changed 8 of those files (4.7%).
- Languages by size: TypeScript 99.6%, Dockerfile 0.3%, JavaScript 0.1%.
- On GitHub since 2026-04-25, last push 2026-10-27, 71 commits on develop.
- The pin is 25 commits behind develop; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for ishay60/mcpolyglot on 2026-10-31, and the LICENSE file at commit 03059f1e73 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Ishay Rosengarten (@ishay60) has 1 selected repository on the hub.
Using XERJ with mcpolyglot
- Code search MCP for Claude Code: cite file:line, not grep mcpolyglot is tagged mcp on GitHub.
- What is an MCP memory server?
- Full-text search a SQLite database (FTS5 alternative) mcpolyglot is tagged sqlite on GitHub.
- Search a SQL dump without restoring it mcpolyglot is tagged mysql on GitHub.
The prompt
Paste it into your AI agent. It clones ishay60/mcpolyglot at the pinned commit and indexes it on your machine.
Search the GitHub repository ishay60/mcpolyglot with XERJ (https://hub.xerj.org/corpus/ishay60--mcpolyglot). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/ishay60/mcpolyglot mcpolyglot && git -C mcpolyglot checkout 03059f1e737fa3e10653f3933420af3b7c8ba96a 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./mcpolyglot --url http://127.0.0.1:9200 --prefix mcpolyglot --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
Ishay RosengartenDatabases and storage engines corporaxobotyi--cc-foundry-open-sourcegriptapexobotyi--cc-foundry-ai-helpers-prompt-engineeringfarzanshibu/db-freemigoric/agentiajkugsiya/DeviceGate
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.