Agentic AI securityAn MCP gateway for every agent call
Don’t just govern your agents. Stop them mid-call.
Every agent→MCP call passes through the AtmanID gateway inline — checked against the agent’s scope and blocked before it reaches the server, with humans and agents on one tamper-evident audit trail.
Checked inline, on every call
- token
- agent status
- owner
- scope
- rate limit
- data-loss rules
- approval holds
- agentInvoice Triage Agent → netsuite.
update_ vendor_ bank_ details - gatewaytoken valid · agent ACTIVE · owner: Finance
- gatewayscope check ✗ tool is outside the agent's granted scope
- resultDENY · INSUFFICIENT_
SCOPE · never reached the NetSuite server - auditdecision recorded on the hash-chained audit trail
AtmanID in a minute.
Why agents need identity and access management, and how AtmanID checks every call they make. See it in the product →
Read the transcript
- Your AI agents already have access. To your code, your customers, and your money. And nobody approved most of it.
- AtmanID checks every call an agent makes, before it reaches the tool.
- An agent tries to change a vendor’s bank details. Refused. The same agent reads an invoice. Allowed. Decided per call, not per agent.
- People and agents share one identity model. One lifecycle. One set of access reviews. And you can ask who can do what, and why.
- Every allow, every deny, every approval goes on one hash-chained record. When the auditor asks, evidence is a query.
- AtmanID. Identity and access management for people and AI agents.
Compliance posture — stated honestly, verifiable on the Trust page
SOC 2
Not yet audited
Self-assessed; detail on the Trust page
NIST 800-53
Controls mapped
Per-control coverage matrix
GDPR
Tooling built in
Erasure · retention · DPA on request
Tenant isolation
Database-enforced
Row-level security, probed per schema change
Audit chain
Tamper-evident
Hash-chained, append-only
API contract
OpenAPI 3.1
Semver · 6-mo deprecation
Capabilities
Built for the moment an agent acts.
Identity tools decide who gets a token. AtmanID also decides what happens next: every call, every lifecycle change, on one record.
Inline enforcement
Stop the call, not just the credential.
Every agent-to-tool call passes through the AtmanID gateway and is checked against that agent’s scope, rate limits and data-loss rules, so an invoice agent with a valid NetSuite token still can’t change a vendor’s bank details. Calls that fail are refused before they reach the server; responses are inspected on the way back. Start in shadow mode to see what would be blocked, then enforce.
- zendesk.get_ticketSupport CopilotALLOW
- snowflake.run_queryData Pipeline AgentALLOW
- github.list_commitsDeploy BotDENY · RATE_LIMIT_AGENT_SERVER
- salesforce.export_reportmarketing-gptWOULD_DENY · AGENT_INACTIVE
Illustrative. The last call ran in shadow mode: recorded as WOULD_DENY, not blocked, so you see the impact before enforcing.
One identity model
Humans and agents, one lifecycle.
Agents get the same joiner, mover and leaver workflows as people, plus an accountable owner, approvals, access reviews and separation-of-duties checks. When someone leaves, the agents they own are deactivated or reassigned in the same sweep.
- eventleaver · Dana Lee · Finance
- ownsInvoice Triage Agent, AP Reconciliation Bot
- agentsdeactivated with their owner, or reassigned
- accessNetSuite, Gmail, Snowflake → revocation queued
- auditeach step recorded on the audit trail
Illustrative. When a person leaves, the agents they own leave with them — one sweep, not two systems to reconcile.
Tamper-evident audit
Every decision, provable.
Allowed and denied calls, approvals and lifecycle changes land on one hash-chained, append-only audit trail. Evidence for an auditor is a query, not a quarterly project.
- #1281 ACCESS_REQUEST_APPROVEDprev 7c1e…a90f → hash b42d…1c07
- #1282 AGENT_SUSPENDEDprev b42d…1c07 → hash e9a0…5d33
- #1283 AGENT_DEACTIVATEDprev e9a0…5d33 → hash 03fb…88e2
chain verified · no gaps, no edits
Illustrative. Each entry carries the hash of the one before it, so a deleted or altered entry breaks the chain visibly.
Plain-English answers
Ask, within your own permissions.
Ask who can do what, why they have it and when it was last used. Answers come from your live data and never exceed your own role; anything that changes access still goes through approval.
What do you want to know?
- Who can change vendor bank details in NetSuite?
- Which agents haven’t used their access in 30 days?
- Grant me admin on github-prod.
you > Who can change vendor bank details in NetSuite?
3 identities hold that permission: 2 people in AP, 1 agent.
· the agent was granted it 41 days ago and has not used it since
· suggested: revoke — opens an access review for its owner
Everything in the platform today
Enforce
7 controls on every call
- Inline MCP gateway on every agent tool call watch it →
- Per-tool scope checks
- Per-agent and per-server rate limits
- Built-in and custom data-loss rules
- Shadow mode before enforce
- Human approval holds for risky actions
- Short-lived, revocable agent tokens
Govern
6 lifecycle workflows
- Joiner, mover, leaver for humans and agents watch it →
- Accountable owner for every agent
- Access requests and approval workflows watch it →
- Access reviews and certifications
- Separation-of-duties detection watch it →
- Break-glass access with review
Prove
4 kinds of evidence
- Hash-chained, append-only audit trail
- SOC 2 evidence packs on demand watch it →
- Controls mapped to compliance frameworks
- Personal-data export and erasure requests
Integrate
5 kinds of integration
- 12 connectors: AWS, Entra, GCP, Okta, GitHub and more
- SCIM provisioning
- REST API with a versioned OpenAPI 3.1 spec
- TypeScript SDK and GitHub Action
- Signed outbound webhooks
Platform
3 safeguards
- Tenant isolation enforced in the database
- KMS envelope encryption for secrets
- Passkeys and multi-factor sign-in
Agents in production
What goes wrong when agents act on their own, and what stops it.
AtmanID decides on each tool call that passes through its gateway, so these are caught while the agent is running, not in next quarter's review. It sits alongside Okta, Entra and SailPoint: keep them for sign-in and governance, add AtmanID where agents act. New rules can start in warn mode.
An agent stuck in a loop hammers an API, or issues refund after refund.
Each agent has a call-rate limit, overall and per server, and a policy can cap what it moves through a tool each day.
support-agent → stripe.
create_ refund { amount: 40 } daily refund cap: 4,980 of 5,000 used
RefusedINTENT_
DENY Instructions hidden in a tool description or another agent’s output steer an agent off course.
A steered agent still reaches only the tools it was granted. Poisoned tool descriptions are flagged, and so is data read from one server and sent to another.
research-agent ← billing.
get_ invoice · response carries a card number research-agent → mail.
send_ email FlaggedTAINTED_
SESSION A payment, a deletion or a permission change should not happen without a person saying yes.
Policies hold the call, on the action or its arguments, until an approver decides. One approval releases one call.
billing-agent → stripe.
create_ refund { amount: 1200 } policy: refunds over 500 need approval
Heldwaiting for an approver
On the way to an answer, an agent reaches for a tool it was never meant to use.
Every call through the gateway is checked against the agent’s scope and intent policy, and refused before it reaches the tool.
deploy-agent → github.
delete_ repo intent policy: deploy-agent may not delete
RefusedINTENT_
DENY An agent goes beyond what it was given, or its credentials are in the wrong hands.
Scope probing, dormant keys bursting into activity and delegation laundering raise detections. The response holds, suspends or kills the agent: as a recommendation first, then on its own.
detection: idle for weeks, then a burst of calls
kill switch: tokens revoked · next call
RefusedTOKEN_
REVOKED
Use cases
The problems security teams bring to AtmanID.
Six situations where agents and access go wrong, from payment fraud to offboarding, and what AtmanID does about each one.
See the six use cases
How it works
From first agent to enforced policy in four steps.
Put the gateway in front of your MCP servers, give every agent an owner and a scope, watch in shadow mode, then enforce.
See how it works
Try it
You are the Invoice Triage Agent. Make a call.
Its owner granted it read access to NetSuite and nothing else. Pick a call and watch the gateway decide.
Pick a call to send it through the gateway.
A scripted example of real gateway checks. In SHADOW mode the gateway records each of these as a would-deny and lets the call through, so you can see what enforcement would do before you turn it on.
Early access program
Free early access for five teams running AI agents in production.
What you get
- · Early access to AtmanID, set up with your team
- · A direct line to the founder and a real say in the roadmap
- · Free for the duration of the program
What we ask
- · A named owner on your side and a short check-in every two weeks
- · Honest feedback on what works and what does not
Check it yourself
See our security posture
Public Trust page with the subprocessor inventory, security commitments, and our own control-by-control SOC 2 self-assessment.
Self-assessed against the SOC 2 criteria · not yet audited
View security posture
Browse our REST API
Interactive OpenAPI 3.1 explorer powered by Scalar — every endpoint, every scope, every response. No login required to read the spec.
v1.42.0 · 63 API operations · semver + 6-month deprecation policy
Open the explorer
Govern AI agents like first-class identities
Same Joiner / Mover / Leaver primitives for non-human identities. GitHub Action consumer ships GitOps lifecycle out of the box.
POST /api/v1/agents · idempotency keys · managed_by ownership scoping
See the NHI quickstart
How often we ship
Versioned changelog with type-tagged change entries, plus a machine-readable feed for codegen and dashboards.
50 API releases · latest v1.42.0 on 2026-11-17
Read the changelog
Why AtmanID
One record for every identity — person or agent.
Every agent is tied to the person accountable for it, in the same record as that person’s own access. So the gateway knows who an agent is acting for on every call, an owner’s departure takes their agents’ access with them, and one tamper-evident audit trail answers for both. Audit-readiness becomes part of normal operations, not a quarterly project.
Ātman is Sanskrit for the true self: the one identity behind every account, key and agent session.
Built for identity admins, CISOs, platform engineers and auditors.
Pick your next step.
Talk to us
Direct line to the founder. Best for technical evaluation, custom-control questions, or pilot scoping.
hello@atmanid.com
Browse the developer portal
OpenAPI 3.1 spec, interactive explorer, GitHub Action recipe, MCP integration. No login required.
Open /developers
Request a security review
Questionnaire answers and an architecture walkthrough under NDA. No SOC 2 report yet — we say so up front.
Request a review
Read security commitments
Public Trust page: subprocessors, security architecture, certifications, customer obligations.
Open /trust





