dedalus-mcp-python

dedalus-mcp (Dedalus MCP) is a Python framework for building MCP (Model Context Protocol) clients and servers. It provides ergonomic decorators and registration for MCP tools, resources, prompts, and related capabilities, plus streamable HTTP and stdio transports and support for protected servers (e.g., DPoP) as described in the README.

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ DevTools mcp python framework client server tooling async http stdio dpop security
⚙ Agent Friendliness
52
/ 100
Can an agent use this?
🔒 Security
66
/ 100
Is it safe for agents?
⚡ Reliability
26
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
62
Error Messages
0
Auth Simplicity
55
Rate Limits
0

🔒 Security

TLS Enforcement
85
Auth Strength
70
Scope Granularity
60
Dep. Hygiene
60
Secret Handling
50

The README claims spec-faithful behavior and describes protected transport scenarios (DPoP) and a provider-based authorization framework with scope requirements. However, the provided content does not include concrete implementation details for TLS enforcement, structured error codes, secret handling practices, or dependency security posture—scores reflect partial evidence from README/manifest only. The library depends on pydantic and MCP SDK and uses pyjwt[crypto], implying crypto operations but not guaranteeing secure defaults.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
30
Error Recovery
40
AF Security Reliability

Best When

You have an async Python environment and want spec-faithful MCP client/server behavior with decorators and clean server-side registration, and you already have your own deployment/auth/logging stack.

Avoid When

You want minimal learning overhead with no transport/protocol considerations, or you need a fully turnkey auth provider/CLI scaffolding experience.

Use Cases

  • Implement MCP servers that expose tools/resources to MCP clients
  • Build MCP clients that discover and call MCP tools
  • Integrate MCP into existing Python async services (script-style registration and async client usage)
  • Use roots / filesystem boundary concepts to restrict tool access to allowed paths (as described)
  • Use structured auth integrations (e.g., DPoP/auth provider configuration as described)
  • Create multi-server tool registration flows where the same tool can be collected by different server instances

Not For

  • Turnkey production auth/middleware you want enabled without integrating your own IdP/stack
  • Non-Python environments (framework is Python-only)
  • Simple single-endpoint HTTP APIs without MCP semantics (it’s specialized for MCP)
  • If you need OpenAPI/GraphQL-first API surface rather than MCP transport/protocol

Interface

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

Authentication

Methods: AuthorizationProvider (provider-based validation as described) DPoPAuth (client-side helper for protected servers as described) AuthorizationConfig / required_scopes configuration as described
OAuth: No Scopes: Yes

The README describes an OAuth-like JWT/DPoP authorization framework conceptually, plus client support for DPoP. Specific OAuth/OIDC flows beyond the README aren’t fully evidenced in the provided text.

Pricing

Free tier: No
Requires CC: No

Open-source MIT license indicated; no hosted pricing is described in the provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Auth and transport behavior may require careful configuration (e.g., DPoP/protected server settings)
  • MCP tool calling semantics are RPC-like; retries may need idempotency at the tool level (no explicit idempotency/retry guidance evidenced in provided text)

Alternatives

Full Evaluation Report

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

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