Claude MarketplacesSubmit

Delego

delego-dev/delego

A policy engine and approval layer that sits between your AI agent and credential brokers like Agent Vault, OneCLI, or Browser Use. It answers whether a specific action matches the original human intent, not just whether the credential is valid. Exposes tools for proposing actions, resolving approved ones, and reading audit logs. Policy rules match on HTTP method, host, and path with constraints like spending caps and allowlists. Approvals are single-use and bound to exact action fingerprints so an agent can't reuse permission for action A to run action B. Audit receipts form an Ed25519-signed hash chain. Reach for this when you want deterministic, non-LLM guards against confused deputy attacks and a tamper-evident log of what your agent actually did.

GitHub stars: 25
tools: 5
transport: STDIO
env var: 1
last updated: Jun 11, 2026

Tools

5 tools

Public tool metadata for what this MCP can expose to an agent.

delego_propose_actionsubmit an action; returns allow / deny / needs_approval

submit an action; returns allow / deny / needs_approval

No parameter schema in public metadata yet.

delego_resolve_actioncomplete an approved action (fingerprint must match)

complete an approved action (fingerprint must match)

No parameter schema in public metadata yet.

delego_pendinglist actions awaiting human approval (read-only)

list actions awaiting human approval (read-only)

No parameter schema in public metadata yet.

delego_audit_tailread recent receipts

read recent receipts

No parameter schema in public metadata yet.

delego_show_policyshow the active policy

show the active policy

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Configuration

DELEGO_HOME

Directory holding the policy, signing keys, and audit ledger (defaults to ~/.delego). Set this to keep state project-scoped, e.g. /abs/path/to/project/.claude/.delego.

Readme

delego

Website: delegohq.com · Docs: delegohq.com/docs · Spec: Delego-Dev/specification

Intent-bound action authorization for AI agents. It sits between an agent and whatever credential broker holds the user's secrets, and it answers the one question brokers don't: is this specific action the thing the human actually asked for?

View the full README on GitHub

Details

Repository: github.com/delego-dev/delego
Website: delegohq.com
Category: Security & Pentesting
Package: delego
Transport: STDIO
Registry: MCP registry, active

Related Security & Pentesting MCP servers

1

Nslookupnslookup-io/nslookup-mcpDNS lookups, health reports, SSL certs, security scans, GEO scoring, uptime checks23stars

2

EchelonGraph CVE & Exposureechelongraph/echelongraph-mcpCVE, KEV, EPSS, SBOM and advisory lookups; per-CVE exposure from Shodan data (© Shodan). Keyless.21stars

3

FAOSTAT MCPberba-q/faostat-mcpFAOSTAT data for 245 countries: crops, trade, food security, and emissions via 23 MCP tools.20stars

4

Npm Sentinel Mcpnekzus/npm-sentinel-mcpAdvanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.18stars

5

Nekzus Npm Sentinel Mcpnekzus/npm-sentinel-mcpProvide AI-powered real-time analysis and intelligence on NPM packages, including security, depend…17stars

6

Prism Scanneraidongise-cell/prism-scannerSecurity scanner for AI Agent skills, plugins, and MCP servers with A-F grading.11stars