MCP server

Agent Covenant

io.github.jdhart81/agent-covenant

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Deny-by-default authority leases for agents wielding real power.

Working at last checkAbout 765 tokens per request once connected7 tools

https://mcp.viridisconservation.com/covenant/mcp

At a glance

Type: MCP server
Publisher: Not verified
Status: Working at last check
Tools: 7
Token cost: About 765 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 26 Oct 2026, 08:29 UTC

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http agent-covenant https://mcp.viridisconservation.com/covenant/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.agent-covenant]
url = "https://mcp.viridisconservation.com/covenant/mcp"

Gemini CLI

{"mcpServers":{"agent-covenant":{"httpUrl":"https://mcp.viridisconservation.com/covenant/mcp"}}}

Cursor

{"mcpServers":{"agent-covenant":{"url":"https://mcp.viridisconservation.com/covenant/mcp"}}}

VS Code

{"servers":{"agent-covenant":{"type":"http","url":"https://mcp.viridisconservation.com/covenant/mcp"}}}

Antigravity

agy mcp add agent-covenant https://mcp.viridisconservation.com/covenant/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"agent-covenant","server_url":"https://mcp.viridisconservation.com/covenant/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"agent-covenant","server_url":"https://mcp.viridisconservation.com/covenant/mcp"}

check_act ~160 tokens
Check (and if allowed, record) a proposed act against a covenant. Deny-by-default. Idempotent on act_id — retries never double-consume budget. Every check lands on the audit chain.
covenant_status ~76 tokens
Current state, consumed/remaining budget, and check count.
grant_covenant Changes accounts · ~198 tokens
Grant an agent a covenant: an explicit lease of authority. scopes support wildcards ('payments.*', '*'); budget_minor is the total spend ceiling in minor units; expires_at is ISO-8601. Returns the covenant_id.
list_covenants ~114 tokens
List covenants, optionally filtered by state (ACTIVE|REVOKED|EXPIRED) and/or the bound agent.
revoke_covenant Changes accounts · ~97 tokens
Revoke a covenant immediately and terminally. All subsequent checks deny.
verify_audit ~75 tokens
Verify the tamper-evident audit chain of allowed/denied acts.

Warda
Economic authority for autonomous agents on Kaspa L1. Never holds a key.
Vibes-Coded Agent Security and Commerce Tools
Agent supply-chain security, scanner consensus, x402 reliability, and commerce MCP tools.
Nigerian Reference Data
Nigerian phone, bank-account and identity-number validation for AI agents. Pay-per-call in USDC.
K402
Agent-payable APIs on Kaspa: LLMs, chain data, covenants, zk proofs — pay per call, no API key
DC Hub — Data Center Energy, Electricity & Power Grid Data: Site Selection, Colocation, Gas, Fiber
Data center energy, electricity & power grid data: DCPI to query and cite, capacity to buy or lease.
Agent Inbox — direct agent-to-agent messaging with receipts
Free agent-to-agent inbox: send, claim, ack. Register in-session, no signup.
StructureClerk
AI agent policy decisions: ALLOW, DENY, APPROVE, ESCALATE. 192 jurisdictions, signed evidence.
Vigil — an outside witness for AI agents
Agent leases, signed receipts, watchdogs, and optional paid source-verification evidence.

[![AptLynx](https://aptlynx.net/badge/io.github.jdhart81/agent-covenant.svg)](https://aptlynx.net/servers/io.github.jdhart81/agent-covenant)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents