mcp-server

Spring AI MCP server that exposes MCP tools over JSON-RPC, primarily via an HTTP endpoint at /api/v1/mpc (and also supports an SSE transport). It auto-discovers tool methods annotated with Spring AI MCP annotations and provides example calculator and rock-paper-scissors tools.

Evaluated Apr 04, 2026 (16d ago)
Repo ↗ DevTools mcp spring-ai json-rpc http sse java tool-discovery
⚙ Agent Friendliness
45
/ 100
Can an agent use this?
🔒 Security
27
/ 100
Is it safe for agents?
⚡ Reliability
25
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
65
Error Messages
0
Auth Simplicity
15
Rate Limits
5

🔒 Security

TLS Enforcement
30
Auth Strength
10
Scope Granularity
0
Dep. Hygiene
50
Secret Handling
55

README does not mention TLS requirements, authentication/authorization, request validation, or rate limiting. If deployed, it should be placed behind TLS termination, protected with auth, and shielded from untrusted traffic. Randomized game tools and expression evaluation for calculator may require input validation depending on implementation details.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
30
Error Recovery
25
AF Security Reliability

Best When

Used in a controlled environment (local dev / trusted network) where an agent needs simple deterministic tools and can connect via the documented MCP HTTP endpoint.

Avoid When

Avoid exposing the HTTP endpoint publicly without adding authentication, network controls, and rate limiting; also avoid for workloads requiring long-term stability guarantees without further verification.

Use Cases

  • Integrating basic computational and game-like tools into an MCP-compatible client/agent
  • Building a lightweight local MCP service for experimentation (e.g., Cursor MCP client)
  • Extending the server with additional annotated tool functions

Not For

  • Production deployments requiring authentication, authorization, and strong security controls
  • Handling untrusted user inputs without additional validation/sandboxing
  • Use cases needing formally specified OpenAPI/SDK contracts beyond the README examples

Interface

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

Authentication

OAuth: No Scopes: No

No authentication/authorization mechanism is described in the README. The example curl requests do not include auth headers.

Pricing

Free tier: No
Requires CC: No

No hosted pricing information; appears to be a self-hosted open-source project.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • No authentication details are provided; agents should assume the endpoint is unauthenticated unless the deployment adds security.
  • Some tools use randomness (e.g., rockPaperScissors/getRandomChoice), so repeated calls will yield different results.
  • Tool discovery depends on correct @Service and @Tool annotations; otherwise tools may not appear.

Alternatives

Full Evaluation Report

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