Add Zeeker legal dataset configuration#44
Open
houfu wants to merge 1 commit into
Open
Conversation
|
All contributors have signed the CLA ✍️ ✅ |
Author
|
I have read the CLA Document and I hereby sign the CLA |
Author
|
Recheck |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds Zeeker to
regulatory-legal/.mcp.json— a read-only remote MCP server exposing four curated Singapore legal datasets from data.zeeker.sg. Addresses the "regulatory primary sources from official registers" gap noted in CONNECTORS.md, scoped to Singapore.The change
Single insertion in
mcpServers:https://mcp.zeeker.sg/mcp2025-06-18)recommendedCategoriesbyte-identical to upstreammainWhat it exposes
Four datasets — judgments (eLitigation), PDPC enforcement decisions and guidelines, SG government newsroom press releases (MinLaw, PDPC, ACRA, IPOS, MOM, AGC, CCS, Judiciary), and sglawwatch commentary — surfaced through six tools:
list_databases,list_tables,describe_table,search,query_table,fetch. Full tool docs: https://mcp.zeeker.sg/docs/tools/. README with example agent workflows (PDPC lookup, cross-database commentary search, newsroom monitoring): https://github.com/houfu/zeeker-mcp/blob/main/README.md.Each response is wrapped in a citation-ready envelope:
provenance.source = data.zeeker.sg, per-row_citation, heavy text isolated inretrieved_contentwith inline_policylicense re-disclosure, and the canonical injection-resistance trailer on every tool description. Details: https://mcp.zeeker.sg/docs/injection-resistance/.Operational notes
rate_limitederror withretry_after_ms— https://mcp.zeeker.sg/docs/rate-limits/Validation
type → url → title → description; key name (Zeeker) equalstitletypeis"http"(not"streamable-http")recommendedCategoriesbyte-identical to upstreammainpython -m json.tool < regulatory-legal/.mcp.jsonparses cleanly;scripts/lint-tool-scope.pyexits 0https://mcp.zeeker.sg/mcp(initialize,tools/list, onetools/callper tool): https://github.com/houfu/zeeker-mcp/blob/main/tests/manual/PHASE9-PR-PROBE.md — verified 2026-05-17 from SG and independently corroborated from Anthropic's network (Claude Code WebFetch) for/docs/,/privacy,/healthz. No IP allowlist.Note:
scripts/validate.pyis the managed-agent worker-output schema validator (validate.py <output.json> <schema.json>) and isn't applicable to.mcp.jsoncontributions — happy to be corrected.Scope
regulatory-legalonly. Adding tolaw-student/legal-clinicdeferred to a follow-up for smaller review surface.recommendedCategoriesuntouched; asingapore-lawtag can be proposed separately if reviewers want one.CLA
Will sign on the bot's first comment with the standard phrase.