mcp-sse

Provides a reference implementation of MCP (Model Context Protocol) tools transported over Server-Sent Events (SSE). It includes an example SSE-based MCP server (weather tools backed by external weather services) and a standalone MCP client that connects to the SSE endpoint and invokes the server’s tools.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ DevTools mcp sse python agents tool-use reference-implementation
⚙ Agent Friendliness
41
/ 100
Can an agent use this?
🔒 Security
30
/ 100
Is it safe for agents?
⚡ Reliability
18
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
60
Error Messages
0
Auth Simplicity
40
Rate Limits
10

🔒 Security

TLS Enforcement
30
Auth Strength
20
Scope Granularity
10
Dep. Hygiene
55
Secret Handling
45

README only indicates an external API key (Anthropic) via env/.env for the example workflow; it does not describe SSE endpoint authentication, authorization, or transport security requirements. TLS/HTTPS and header-level protections are not specified in the provided materials. Dependency list is given but no vulnerability/patch status is provided, so hygiene is estimated.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
20
Error Recovery
20
AF Security Reliability

Best When

You want a working pattern for SSE transport with MCP and you can run the server/client in a controlled environment (e.g., internal network) while adapting the example code.

Avoid When

You need a turnkey, well-specified API product with documented authentication, rate limiting, and operational/SLA guarantees.

Use Cases

  • Running an MCP tool server as a long-lived process and connecting multiple clients to it
  • SSE-based transport for MCP tool invocation (cloud-native decoupled server/client deployments)
  • Building agent-tool integrations that call weather/forecast style functions via MCP

Not For

  • Production-grade, security-hardened deployment without further work (no clear auth model, transport/security posture, or operational guarantees described here)
  • Public internet exposure without network-level controls
  • Environments requiring strict compliance documentation (not provided)

Interface

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

Authentication

Methods: Environment variable API key (ANTRHOPIC_API_KEY mentioned in README for tool usage in the example)
OAuth: No Scopes: No

README mentions supplying an Anthropic API key via environment/.env, but it does not describe authentication for the MCP SSE endpoint itself (i.e., no clear server-side access control is documented).

Pricing

Free tier: No
Requires CC: No

No pricing information is provided; this appears to be an open-source reference pattern.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • No explicit guidance is provided on authentication/authorization for connecting to the SSE endpoint.
  • No explicit retry/idempotency guidance is documented for tool calls.
  • The README demonstrates example tool invocation but does not document server tool schemas/edge cases in detail.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-sse.

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 2026-03-30.

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