Every tool call. Intercepted before execution.

AI agents don't just use MCP. They execute shell commands, read files, search code, call APIs. Oktsec monitors both channels simultaneously.

MCP Gateway

fetch_readable fetch_json fetch_html read_file write_file search_files fetch_markdown fetch_txt + any custom tool

CLI Hooks

Read Write Bash Edit Glob Grep WebFetch WebSearch Agent
Nobody else monitors both channels.

Once intercepted, every call hits the detection engine.

188 rules. 15 categories. Zero LLM guessing.

Every rule is a deterministic YAML pattern or a specialized analyzer. No probabilistic classification, no model drift, no prompt sensitivity. The pipeline runs in microseconds.

Prompt injection Data exfiltration Credential leak Supply chain Command execution MCP attacks SSRF/Cloud Unicode/Homoglyph Tool call security MCP tool-call inspection External downloads Config security Third-party content Inter-agent protocol NLP semantic analysis
10-stage pipeline runs before every tool call. 4 verdicts: clean, flag, quarantine, block.

The pipeline returns one of four verdicts.

Clean. Flag. Quarantine. Block.

Every tool call gets exactly one verdict. The verdict determines what happens next.

Clean

Deliver normally

No rules triggered. The call proceeds to the backend.

Flag

Deliver + warn

Low-severity match. The call proceeds but appears in the dashboard with a warning.

Quarantine

Hold for review

High-severity match. The call is held until a human approves or rejects it. HTTP 202.

Block

Reject immediately

Critical threat detected. The call never reaches the backend. The agent receives an error.

Verdict escalation is automatic. 3+ blocks from the same agent in 1 hour escalates the next flag to quarantine. No ML required — just pattern counting.

Every verdict is logged. Permanently.

Full audit trail. Signed and hashed.

Every tool call produces an immutable audit entry with SHA-256 hash chain and Ed25519 proxy signatures. Export to CSV, JSON, or SARIF.

audit.log
{ "timestamp": "2026-03-13T14:37:51Z", "from_agent": "agent-05", "tool": "Write", "arguments": "config.yaml (AWS_SECRET)", "content_hash": "sha256:a3f8c1...", "verdict": "block", "rules_triggered": ["credential-leak-aws-key"], "scan_latency": "0.6ms", "session_id": "ses_8f2a1b3c" }

Forensics

Reconstruct the full sequence of agent actions across sessions. Identify exactly which tool call triggered which rule.

Integrity

SHA-256 hash chain means any tampering breaks the chain. Ed25519 signatures prove provenance.

Compliance

EU AI Act, NIST AI RMF increasingly require audit trails for AI systems. SARIF export integrates with existing GRC tooling.

When the rule engine flags something suspicious, the optional LLM layer goes deeper.

Threats evolve. So do the rules.

When the rule engine flags suspicious traffic, an optional LLM layer analyzes the context, confirms the threat, and generates new detection rules for human review.

Traffic
188 Rules
Suspicious?
LLM Analysis
Confirm
New Rule Generated

Rules decide what happens. Access control decides who can try.

Zero-trust agent identity.

Every agent gets an Ed25519 keypair. No shared secrets, no bearer tokens, no trust-by-default. Fine-grained controls govern what each agent can do.

Ed25519 keypairs

Per-agent cryptographic identity. Every request is signed and verified.

Per-agent ACL

Define which tools each agent can access. Deny by default, allow explicitly.

Tool allowlists

Restrict agents to specific MCP tools. Block filesystem, network, or shell access per agent.

Spending limits

Per-agent and global budget caps for LLM threat intel. Prevents runaway API costs.

Rate limits

Per-agent request throttling. Prevents denial of service from compromised agents.

Approval thresholds

High-severity actions require human approval. Configurable per verdict level.

Agent suspension is instant. One command revokes an agent's keypair and blocks all further tool calls.

How do you know your deployment is secure?

One command. Full deployment audit.

The oktsec audit command evaluates your agent infrastructure against 41 deployment checks and returns a letter grade with actionable findings.

$ oktsec audit
Security Posture: B (78/100) CRITICAL MCP server "filesystem" has no ACL restrictions HIGH Audit log rotation not configured HIGH No webhook alerts configured for block verdicts PASS Ed25519 keypair configured for all agents PASS Hash chain integrity verified (1,247 entries) PASS Detection rules up to date (188/188) PASS Gateway TLS enabled PASS Rate limits configured ... 33 more checks passed Run 'oktsec audit --fix' to auto-remediate 2 findings.

Built for production.

Performance benchmarks and deployment options for teams running agents at scale.

5,500 msg/sec

Throughput

Messages processed per second through the full 10-stage pipeline

90,000/sec

Batch writes

Audit log batch write throughput to SQLite

~50µs

Signature sign

Ed25519 signature generation per audit entry

~120µs

Signature verify

Ed25519 signature verification per entry

<6ms

Query latency

Dashboard queries at 1M+ rows in the audit database

Single binary

Deployment

Zero CGO, zero runtime dependencies, cross-platform Go binary

Deployment modes

Oktsec adapts to your infrastructure. Run it as a turnkey solution, a gateway, a proxy, or integrate it into your existing MCP setup.

Mode Command Description
Turnkey oktsec run Auto-discovers MCP servers, generates config, starts gateway + dashboard + hooks. Zero to full visibility in 30 seconds.
Gateway oktsec gateway Standalone MCP security proxy. Sits in front of any MCP server and intercepts all tool calls.
Proxy oktsec serve HTTP reverse proxy mode. Forward traffic through Oktsec for inspection and logging.
Stdio oktsec proxy Stdio transport proxy for MCP servers that use stdin/stdout communication.
MCP Server oktsec mcp Run Oktsec itself as an MCP server. Query the audit trail, check security posture, manage rules from any MCP client.
Audit oktsec audit Offline security posture assessment. 41 checks, letter grade, auto-remediation suggestions.

See everything your agents execute.

One command. 30 seconds to full visibility.

Install Now