ralf-fyndling
mcpsmithery# fyndling-mcp Built for **medieval market fans, reenactors, and living-history enthusiasts** — and the AI assistants that help them plan. Fyndling MCP gives AI clients direct access to two niche European datasets: - **Medieval events** — query 2,000+ markets, concerts, castle experiences, and living-history events across 20 European countries by **location + radius + date range** (updated weekly) - **Permanent POIs** — meaderies, mead producers, castles, and medieval restaurants, also searchable by geo-radius - **Historical recipes** — 1,100+ recipes from six cookbooks spanning the 13th–17th century, with modern German adaptations, structured ingredient lists, and original manuscript transcripts → **[fyndling.de](https://fyndling.de)** — the web app behind this data **Endpoint:** `https://fyndling.de/mcp` **Transport:** Streamable HTTP (MCP spec 2025-03-26) **Auth:** none **Rate limit:** 60 requests / minute
By Smithery | 20 findings | Scanned 6/3/2026 | tooltrust-scanner/v0.3.13
Risk Summary
Needs ApprovalDep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (20)
tool declares exec permission
find_events_nearlist_eventsfind_pois_neartool declares network permission
search_recipesFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool name "find_events_near" implies read-only operation but declares exec permission
find_events_neartool name "list_events" implies read-only operation but declares exec permission
list_eventstool name "find_pois_near" implies read-only operation but declares exec permission
find_pois_nearFix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
find_events_nearlist_eventssearch_recipesfind_pois_nearFix: 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.
find_pois_near:tool declares http permission
Fix: 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.
find_events_nearlist_eventsget_eventsearch_recipesget_recipecompose_menulist_recipe_sourcesfind_pois_nearFix: Review and remediate the identified issue.
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 ralf-fyndling"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)