LangGraph-SecureAgents

Deterministic authorization for LangGraph-powered agents.

LangGraph-SecureAgents evaluates authorization in trusted application code and can enforce the decision immediately before a protected Python callable or agent tool executes. LangGraph can orchestrate the agent; an LLM cannot grant itself permissions.

Security model: Authorization is enforced at the callable and agent-tool boundaries you configure. The integrating application remains responsible for authenticating callers, constructing principals from trusted context, mapping each request to the actual resource being accessed, and retaining downstream access controls. See the threat model for the trust boundaries and deployment guidance.

What it provides

• Deterministic policy evaluation with default-deny behavior and explicit-deny rules taking precedence over allow rules.
• Principal- and role-based access control over application-defined actions and resources.
• Callable protection with protect_callable, so authorization is checked immediately before execution.
• Optional LangChain agent middleware that checks tool calls before the tool handler runs.
• Human-approval interrupts for selected sensitive agent actions.
• Fail-closed controls when configured audit callbacks or authorization-related checks fail.

How it fits into an application

The host application authenticates the caller and constructs a trusted Principal. The policy engine then evaluates a concrete action/resource request before a guarded operation proceeds.

Trusted application identity
           |
           v
        Principal
           |
           v
      PolicyEngine
           |
   allow / deny / approval
           |
           v
 Python callable or agent tool
           |
   execute only if authorized

The library does not authenticate users or make untrusted runtime context trustworthy. Those responsibilities stay with the application.

Installation

Requires Python 3.11 or newer.

Install the core policy engine and callable guard:

python -m pip install langgraph-secure-agents

For the optional LangChain/LangGraph agent middleware:

python -m pip install "langgraph-secure-agents[langchain-agents]"

The core policy engine does not require an LLM provider or the optional agent middleware dependencies.

Quick start: evaluate an authorization policy

This example requires no LLM or agent framework.

from langgraph_secure_agents import (
    AccessRequest,
    DecisionReason,
    Effect,
    PolicyEngine,
    PolicyRule,
    Principal,
)

policy = PolicyEngine(
    [
        PolicyRule(
            rule_id="analysts-read-reports",
            effect=Effect.ALLOW,
            roles=frozenset({"analyst"}),
            actions=frozenset({"read"}),
            resources=frozenset({"reports"}),
        )
    ]
)

request = AccessRequest(
    principal=Principal("user-123", roles=frozenset({"analyst"})),
    action="read",
    resource="reports",
)

decision = policy.evaluate(request)

assert decision.allowed
assert decision.reason is DecisionReason.EXPLICIT_ALLOW

A request with no matching allow rule is denied by default. An explicit matching deny rule overrides an allow rule. Use the public DecisionReason enum for machine-readable outcomes rather than matching free-form text.

Protect an existing Python callable

Wrap a function that accesses a protected resource. The resolver must identify the same resource that the function actually accesses.

from langgraph_secure_agents import (
    Effect,
    PolicyEngine,
    PolicyRule,
    Principal,
    protect_callable,
)

report_policy = PolicyEngine(
    [
        PolicyRule(
            rule_id="analysts-read-report-123",
            effect=Effect.ALLOW,
            roles=frozenset({"analyst"}),
            actions=frozenset({"read"}),
            resources=frozenset({"report:123"}),
        )
    ]
)


def current_principal() -> Principal:
    # Replace with trusted, request-scoped identity from your application.
    return Principal("user-123", roles=frozenset({"analyst"}))


protected_lookup = protect_callable(
    lookup_report,  # Your existing function
    policy=report_policy,
    principal_resolver=current_principal,
    action="read",
    resource_resolver=lambda report_id: f"report:{report_id}",
)

# Authorization is checked before the protected function executes.
report = protected_lookup("123")

For multi-user applications, resolve identity from authenticated request context; do not capture one user's identity in a process-wide shared tool. Resolver logic and policy configuration are security-sensitive application code.

Optional agent middleware

Install the langchain-agents extra and add the authorization middleware to a supported LangChain agent:

from langgraph_secure_agents.middleware import create_authorization_middleware

authorization_middleware = create_authorization_middleware(
    policy,
    principal_resolver=resolve_principal,
)

Pass authorization_middleware to the agent's middleware configuration. resolve_principal must construct a Principal from trusted runtime context. By default, the policy action is execute and the resource is the tool name; custom resolvers can map tool calls to domain-specific actions and resources. A denied call returns an error tool message without invoking the tool handler.

For sensitive actions, a policy can use Effect.REQUIRE_APPROVAL to pause execution for a human decision. This requires LangGraph 1.2 or newer with an active checkpointer. The host application must authenticate the reviewer, secure the resume endpoint, and enforce one-time approval consumption for side-effecting operations. An approval fingerprint alone is not proof of reviewer identity or a one-time token.

Security responsibilities

Integrators must:

• Authenticate callers and derive principals and roles from trusted, validated server-side data.
• Apply guards to every path that can invoke a sensitive operation.
• Ensure each resource resolver matches the exact resource and tenant used by the protected operation.
• Keep downstream services and data stores' own authorization controls enabled.
• Configure and operate durable audit storage when audit persistence is required.

This library does not provide authentication, tenant isolation, prompt-injection prevention, secrets management, rate limiting, or a human-reviewer service. Read the threat model and security policy before evaluating it for your use case.

Run the example

The repository includes a model-free LangGraph workflow using mock payroll records. It needs no model API key:

python examples/policy_guarded_workflow.py

The example shows one allowed HR request and two denied requests: one for an unapproved resource and one from a caller without the required role.

Development and testing

Install the development dependencies from a source checkout:

python -m pip install -e ".[dev]"
ruff check .
ruff format --check .
mypy src
pytest --cov=langgraph_secure_agents --cov-report=term-missing --cov-fail-under=98

CI tests Python 3.11, 3.12, and 3.13, checks linting, formatting, and types, and enforces a 98% minimum line-coverage threshold. The packaging workflow also validates the wheel and source distribution and smoke-tests the installed package and optional middleware extra.

Project documentation

• Threat model — trust boundaries, intended mitigations, and remaining application responsibilities.
• Security policy — project status and vulnerability reporting.
• Changelog — user-facing changes by release.
• Releasing — maintainer information about automated releases.

License

MIT. See LICENSE.