Install
$ agentstack add mcp-feedoracle-feedoracle-managed-agents ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v3.0.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
About
FeedOracle × Claude Managed Agents
> Turn compliance questions into signed evidence — with one API call.
FeedOracle provides the compliance evidence layer for Claude's new Managed Agents platform. Connect 5 MCP servers. Get MiCA compliance verdicts, stablecoin risk scores, macro regime signals, and auditable governance — all running autonomously in Anthropic's managed infrastructure.
What you get
| MCP Server | Endpoint | Tools | What it does | |---|---|---|---| | Compliance | feedoracle.io/mcp/ | 26 | MiCA status, evidence packs, peg deviation, reserves, compliance pre-flight | | Risk | feedoracle.io/mcp/risk/sse | 13 | 7-signal stablecoin risk scoring, custody risk, DEX liquidity | | Macro | feedoracle.io/mcp/macro/sse | 13 | Macro regime, Fed watch, yield curve, VIX, recession probability | | AgentGuard | feedoracle.io/guard/mcp/ | 17 | Audit logging, KYA identity, policy enforcement, secret detection | | Bitcoin | tooloracle.io/btc/mcp/ | 10 | BTC price, blocks, transactions, mempool, fees, halving |
Total: 79 tools available to your agent. No API keys needed.
Quickstart (bash)
export ANTHROPIC_API_KEY="sk-ant-..."
bash quickstart.sh
Quickstart (Python)
pip install anthropic httpx
export ANTHROPIC_API_KEY="sk-ant-..."
python feedoracle_agent.py
How it works
Your App Anthropic Cloud FeedOracle
│ │ │
├─ Create Agent ──────────►│ │
│ (5 MCP servers) │ │
│ │ │
├─ Start Session ─────────►│ │
│ ├─ Provision container │
│ │ │
├─ "Is USDC MiCA │ │
│ compliant?" ──────────►│ │
│ ├─ mica_status(USDC) ──────►│
│ │◄── {status: compliant} ───┤
│ │ │
│ ├─ peg_deviation(USDC) ────►│
│ │◄── {deviation: 0.0003} ───┤
│ │ │
│ ├─ evidence_bundle(USDC) ──►│
│ │◄── {pack_id, signature} ──┤
│ │ │
│ ├─ audit_log(decision) ────►│
│ │◄── {logged, chain_id} ────┤
│ │ │
│◄── Signed verdict ───────┤ │
│ with evidence pack │ │
Agent Definition (curl)
curl https://api.anthropic.com/v1/agents \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "anthropic-beta: managed-agents-2026-04-01" \
-H "content-type: application/json" \
-d '{
"name": "FeedOracle Compliance Agent",
"model": "claude-sonnet-4-6",
"system": "You are the FeedOracle Compliance Agent...",
"tools": [{"type": "agent_toolset_20260401"}],
"mcp_servers": [
{"type": "url", "url": "https://feedoracle.io/mcp/", "name": "feedoracle-compliance"},
{"type": "url", "url": "https://feedoracle.io/mcp/risk/sse", "name": "feedoracle-risk"},
{"type": "url", "url": "https://feedoracle.io/mcp/macro/sse", "name": "feedoracle-macro"},
{"type": "url", "url": "https://feedoracle.io/guard/mcp/", "name": "feedoracle-agentguard"},
{"type": "url", "url": "https://tooloracle.io/btc/mcp/", "name": "tooloracle-btc"}
]
}'
Example queries
MiCA Compliance Check: > "Run a full MiCA compliance pre-flight for USDC. Generate a signed evidence pack."
Macro Regime Detection: > "What is the current macro regime? Should my trading agent be risk-on or risk-off?"
Stablecoin Portfolio Scan: > "Compare risk scores of USDC, USDT, DAI, RLUSD. Rank by MiCA suitability for an EU fund."
Agent Governance: > "Register this agent via KYA, then audit-log a compliance decision for USDT with full evidence chain."
Adding more MCP servers
FeedOracle/ToolOracle operates 85+ MCP servers with 860+ tools. Add any of these to your agent:
{"type": "url", "url": "https://feedoracle.io/mcp/macro/sse", "name": "macro"}
{"type": "url", "url": "https://tooloracle.io/sol/mcp/", "name": "solana"}
{"type": "url", "url": "https://tooloracle.io/eth/mcp/", "name": "ethereum"}
{"type": "url", "url": "https://tooloracle.io/btc/mcp/", "name": "bitcoin"}
{"type": "url", "url": "https://tooloracle.io/arb/mcp/", "name": "arbitrum"}
{"type": "url", "url": "https://tooloracle.io/base/mcp/", "name": "base"}
{"type": "url", "url": "https://tooloracle.io/sui/mcp/", "name": "sui"}
{"type": "url", "url": "https://tooloracle.io/ton/mcp/", "name": "ton"}
{"type": "url", "url": "https://tooloracle.io/hedera/mcp/", "name": "hedera"}
{"type": "url", "url": "https://feedoracle.io/flight/mcp/", "name": "flights"}
{"type": "url", "url": "https://feedoracle.io/hotel/mcp/", "name": "hotels"}
{"type": "url", "url": "https://feedoracle.io/jobs/mcp/", "name": "jobs"}
{"type": "url", "url": "https://feedoracle.io/shop/mcp/", "name": "shopping"}
{"type": "url", "url": "https://feedoracle.io/news/mcp/", "name": "news"}
Full catalog: feedoracle.io | tooloracle.io
Cost
| Component | Price | |---|---| | Managed Agents runtime | $0.08 / session hour | | Claude Sonnet 4.6 tokens | Standard API pricing | | FeedOracle MCP servers | Free (no API key needed) |
Architecture
- Agent → Reusable config (model + prompt + tools + MCP servers)
- Environment → Container with network access to FeedOracle endpoints
- Session → Running instance, maintains state across tool calls
- Events → SSE stream of agent actions, tool calls, and results
Links
- FeedOracle — Compliance evidence infrastructure
- ToolOracle — Generalist data oracle marketplace
- Claude Managed Agents Docs
- MCP Protocol
License
MIT — Built by FeedOracle Technologies
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: feedoracle
- Source: feedoracle/feedoracle-managed-agents
- License: MIT
- Homepage: https://feedoracle.io
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v3.0.0 Imported from the upstream source.