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.

Evaluated Apr 04, 2026 (20d ago)
Homepage ↗ Repo ↗ Ai Ml mcp llm web-search url-fetch sse python
⚙ Agent Friendliness
58
/ 100
Can an agent use this?
🔒 Security
37
/ 100
Is it safe for agents?
⚡ Reliability
26
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
70
Error Messages
0
Auth Simplicity
95
Rate Limits
20

🔒 Security

TLS Enforcement
70
Auth Strength
10
Scope Granularity
0
Dep. Hygiene
55
Secret Handling
60

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

Uptime/SLA
0
Version Stability
45
Breaking Changes
30
Error Recovery
30
AF Security 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

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication mechanisms are described in the README. The MCP server appears to run as a local service over SSE.

Pricing

Free tier: No
Requires CC: No

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

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

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered