Delphi MCP Server

Official Delphi MCP server enabling AI agents to interact with Delphi — a platform for creating AI-powered digital twins and expert knowledge clones — querying personalized AI personas trained on expert knowledge, accessing domain-specific answers from Delphi-trained experts, and integrating expert knowledge systems into agent-driven research and consultation workflows.

Evaluated Mar 07, 2026 (0d ago) vcurrent
Homepage ↗ Repo ↗ AI & Machine Learning delphi digital-twin mcp-server ai-persona knowledge-clone expert-system
⚙ Agent Friendliness
70
/ 100
Can an agent use this?
🔒 Security
78
/ 100
Is it safe for agents?
⚡ Reliability
66
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
68
Documentation
70
Error Messages
65
Auth Simplicity
80
Rate Limits
72

🔒 Security

TLS Enforcement
92
Auth Strength
78
Scope Granularity
70
Dep. Hygiene
70
Secret Handling
78

HTTPS enforced. API key. Delphi cloud data handling. Store key as env var.

⚡ Reliability

Uptime/SLA
70
Version Stability
65
Breaking Changes
65
Error Recovery
65
AF Security Reliability

Best When

An agent needs to consult a specific expert's knowledge clone on Delphi — for domain-specific insights trained on a particular person's expertise and content.

Avoid When

You need general AI capabilities or don't have a Delphi subscription — use Claude, GPT, or other LLMs directly for generic tasks.

Use Cases

  • Querying expert knowledge clones for specialized domain answers from research agents
  • Integrating personalized AI advisors into agent workflows from consultation agents
  • Accessing thought leader insights and methodologies from knowledge agents
  • Building expert-backed decision support from enterprise advisory agents
  • Consulting domain specialists via AI personas from professional workflow agents
  • Scaling expert knowledge across teams via AI clones from training agents

Not For

  • Teams without Delphi accounts or digital twin subscriptions
  • General-purpose AI queries (use direct LLM APIs for generic tasks)
  • Real-time data queries (Delphi knowledge clones use static training data)

Interface

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

Authentication

Methods: api_key
OAuth: No Scopes: No

Delphi API key required. Register at delphi.ai for API access. Knowledge clone IDs needed to query specific personas.

Pricing

Model: paid
Free tier: Yes
Requires CC: No

Delphi has paid plans for knowledge clone creation and API usage. MCP server is free. Query costs based on Delphi plan.

Agent Metadata

Pagination
none
Idempotent
Full
Retry Guidance
Not documented

Known Gotchas

  • Delphi knowledge clones are only as good as the training data — quality varies by expert
  • Clone IDs must be known in advance — no dynamic discovery of available personas
  • Training data has a cutoff — clones don't have real-time knowledge of recent events
  • Niche platform — smaller community and less battle-tested than major LLM APIs
  • Official Delphi MCP but ecosystem is still maturing
  • Queries are billed — implement caching to avoid redundant expensive queries

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Delphi 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 2026-03-07.

6470
Packages Evaluated
26150
Need Evaluation
173
Need Re-evaluation
Community Powered