aws-bedrock-mcp-client-server

Spring Boot (deployed on AWS Lambda behind API Gateway) that exposes a REST API to interact with Amazon Bedrock models and leverages MCP-style tool use for tasks such as calculations, weather retrieval (via external weather API), and converting web pages to markdown; includes CDK/IAM provisioning.

Evaluated Apr 04, 2026 (16d ago)
Repo ↗ Ai Ml ai-ml api-gateway aws bedrock mcp serverless spring-boot lambda tool-calling
⚙ Agent Friendliness
34
/ 100
Can an agent use this?
🔒 Security
49
/ 100
Is it safe for agents?
⚡ Reliability
15
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
30
Documentation
55
Error Messages
0
Auth Simplicity
40
Rate Limits
10

🔒 Security

TLS Enforcement
90
Auth Strength
35
Scope Granularity
25
Dep. Hygiene
40
Secret Handling
55

Uses AWS Lambda/API Gateway over HTTPS is typical, but TLS enforcement for the public API is not explicitly stated in the README. Caller authentication/authorization for the REST endpoints is not described. Deployment requires AWS IAM permissions for Lambda/API Gateway/Bedrock; ensure least-privilege IAM. There is an external weather API key requirement—ensure it is stored in AWS Secrets Manager/SSM and not logged. No details provided on input validation, SSRF protections for the webpage URL endpoint, or prompt/tool output sanitization; those are important for security review.

⚡ Reliability

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

Best When

You want a serverless, AWS-native prototype/demo of Bedrock + tool calling via an MCP-like approach, and you can configure/test IAM and operational controls.

Avoid When

You need a well-specified public API contract (OpenAPI/examples), documented auth scheme for callers, strong retry/idempotency semantics, or clear rate-limit behavior out of the box.

Use Cases

  • Tool-using LLM interactions with Amazon Bedrock (multi-step queries)
  • Serverless hosting of an MCP-like workflow that calls model + tools
  • Weather lookups and summarization-style workflows
  • Simple calculation operations via tool endpoints
  • Webpage-to-markdown conversion via an endpoint

Not For

  • Production workloads requiring strict enterprise governance unless IAM, logging, and data handling are reviewed
  • Use cases needing guaranteed idempotency/replay safety (not documented)
  • Environments that require explicit published API rate-limit guarantees (not documented)

Interface

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

Authentication

Methods: AWS IAM credentials/roles for deployment and backend integration (AWS service permissions)
OAuth: No Scopes: No

The README discusses AWS credentials/permissions for deploying and for Bedrock access, but does not document caller authentication/authorization for the exposed REST endpoints (e.g., IAM auth, Cognito, API keys, JWT, etc.).

Pricing

Free tier: No
Requires CC: No

No pricing information provided. Costs likely come from AWS Lambda/API Gateway usage, Bedrock model inference, and the external weather API.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • No documented machine-readable API contract (e.g., OpenAPI) or explicit response/error schema, so agents may need to infer behavior from trial runs.
  • Retry/idempotency semantics for POST endpoints are not documented; agents should be cautious about repeated tool invocations.
  • Rate limiting behavior is not documented; high-throughput agents may see throttling without clear guidance.

Alternatives

Full Evaluation Report

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