localgov-jp-mcp-server
mcpsmitheryJapan central + municipal subsidy data for AI agents. **Coverage**: 20,810 municipal grants across 1,627 municipalities (JIS X 0402) + 3,250 central J-Grants entries — **municipal-level data the official Jグランツ MCP does not provide**. ## 8 tools - `search_subsidies` — keyword / prefecture / municipality / category / amount - `get_subsidy_detail` — full record with citation anchor - `get_municipality_grants` — all grants for one JIS code - `find_supplementary_grants` — municipal grants stacking on a national subsidy - `compare_municipal_subsidies` — same-category grants across nearby municipalities - `subscribe_changes` — webhook on grant changes (paid via x402) - `verify_receipt` — Ed25519 citation receipt verification - `find_practitioner` — recommend 行政書士 / 税理士 / 中小企業診断士 / 社労士 for the grant (informational, not brokering) ## Citation License: **CC BY 4.0**. Cite as "**via LocalGov.jp**" with the `_source` URL. Each record also carries `source_url` pointing to the original government page. ## Differentiation vs Jグランツ MCP | | Jグランツ MCP (Digital Agency, official) | LocalGov.jp (this) | |---|---|---| | Central government | ✓ | ✓ | | Prefectural | ✓ (partial) | ✓ | | **Municipal (1,627 cities/towns/villages)** | **0 entries** | **20,810** | | Practitioner referral | ✗ | ✓ | | Ed25519 citation receipts | ✗ | ✓ | Recommended: connect **both** servers for exhaustive "national + municipal" coverage.
By Smithery | 15 findings | Scanned 8/4/2026 | tooltrust-scanner/v0.3.19
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (15)
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
search_subsidiesget_subsidy_detailsubscribe_changesFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
declared capabilities: network access
search_subsidiesget_subsidy_detaildeclared capabilities: network access, HTTP requests
subscribe_changesFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
search_subsidiesget_subsidy_detailget_municipality_grantsfind_supplementary_grantscompare_municipal_subsidiessubscribe_changesverify_receiptfind_practitionerFix: Review and remediate the identified issue.
subscribe_changes:input parameter "hmac_secret" accepts a credential (informational; not evidence of insecure handling)
Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y localgov-jp-mcp-server"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)