tagny-mcp-server
Provides an MCP server (FastMCP-based) exposing tools for web search (Brave, DuckDuckGo) and web content fetching (URL visible text extraction) plus link extraction from webpages, intended for use with locally served LLMs via SSE transport.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Security posture can’t be fully verified from the provided README/manifest. No auth is described (suggesting open access if reachable). The server fetches arbitrary external URLs and performs HTML parsing/search, which increases the importance of outbound request controls (allowlists/denylists), SSRF protections, and response size limits. Dependency hygiene and secret-handling practices are not documented in the provided content.
⚡ Reliability
Best When
You want a locally hosted MCP toolset for browsing/search to support interactive LLM agents, and you can tolerate the inherent variability of external web sources.
Avoid When
You need robust security controls (auth, domain restrictions), strong operational guarantees (SLA, well-defined retries/idempotency), or predictable request/response formats beyond the described tool outputs.
Use Cases
- • RAG pipelines that need web page content for grounding
- • Agent workflows that need to browse the web and extract relevant text
- • Link discovery/crawling assistance within an LLM agent
- • Lightweight web search augmentation in local LLM environments
Not For
- • High-reliability production crawling at scale without additional controls (rate limiting, caching, allowlists/denylists)
- • Handling of sensitive/regulated data without reviewing outbound network and data retention behavior
- • Strictly offline environments (tools require external network access)
Interface
Authentication
No authentication mechanisms are described in the README. The MCP server appears to run as a local service over SSE.
Pricing
Agent Metadata
Known Gotchas
- ⚠ Web fetching/search depends on external services (sites and search engines), so results can vary and requests can fail due to network/HTML changes.
- ⚠ No authentication/rate-limit details are documented; agents may need to self-throttle to avoid overload.
- ⚠ Fetching and parsing arbitrary URLs can produce unpredictable HTML/redirect behaviors; consider URL allowlists/denylists in the calling agent.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for tagny-mcp-server.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-04-04.