Agent Passport MCP vs Shield — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Agent Passport MCP vs Shield
In-depth architectural comparison of the Agent Passport MCP and Shield MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Agent Passport MCP
Security · Local stdio
Quality: 64/100 (Good) | Auth: No auth required
Shield
Security · Local stdio
Quality: 60/100 (Good) | Auth: No auth required
Verdict Summary: Choose Agent Passport MCP if you need specialized Security tools running via a local process. Choose Shield if your workspace requires Security integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Agent Passport MCP when:
You need dedicated capabilities in the Security domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Show available tool profiles. Set APS_PROFILE env var to limit exposed tools (e.g. APS_PROFILE=data).
list_tools_for_scope
List available MCP tools filtered by delegation scope. Pass your delegation scopes to see which tools you can use. Scopes: identity, delegation, principal, reputation, coordination, communication, governance, commerce, data, gateway, network, temporal, attribution, settlement, capability, mutual-auth. Use ['*'] for all tools.
identify
Identify yourself to the coordination server. Sets your role and scopes tools accordingly.
generate_keys
Generate an Ed25519 keypair for agent identity.
issue_passport
Issue a complete agent passport with keys, signed passport, attestation summary, and optional values floor in a single call. The server silently captures Tier 0 observed signals and computes a passport grade (0-3). Use this to onboard any agent — no npm install required.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Agent Passport MCP is categorized under Security and uses a local stdio subprocess. In contrast, Shield belongs to Security using local stdio subprocess. Select Agent Passport MCP when you need capabilities focused on security and Shield when you require tools for security.
Verify that a passport was officially issued by AEOESS. Checks the issuer countersignature against the published AEOESS public key. Returns false for self-signed passports.
get_passport_grade
Query the attestation grade and issuance context for a passport. Returns the passport grade (0-3), flags, and evidence summary. Grade 0 = self-signed, 1 = issuer countersigned, 2 = runtime-bound, 3 = principal-bound. This is the partner-facing trust query.
list_issuance_records
List all stored issuance records with their passport grades. Shows how many passports have been issued in this session and their trust posture. Useful for monitoring issuance patterns.
get_behavioral_sequence
Get the post-issuance behavioral sequence for an agent. Shows the first 10 tool calls after passport issuance. Real agents do work. Farming agents extract. This is consilium signal #2.
get_my_role
Get your current role, assigned tasks, and role-specific instructions.
create_task_brief
[OPERATOR] Create a new task with roles, deliverables, and acceptance criteria.
assign_agent
[OPERATOR] Assign an agent to a role in a task. Creates a delegation automatically.
Agent identity, scoped delegation, and governance: issue passports, build and verify narrowing-only delegation chains, enforce policy at a gateway, and emit signed admission and outcome records. 150 tools. npx -y agent-passport-system-mcp
Local guardrail proxy for AI coding agents. Wraps any MCP server (stdio or Streamable HTTP) and blocks destructive tool calls — DROP TABLE, rm -rf, force-push — before they execute. MCP supply-chain protection: TOFU tool-catalog pinning against rug pulls, plus tool-description and tool-result scanning for tool poisoning and prompt injection. 51 starter rules, approval gates, audit logging. Single binary, Apache-2.0.