Connect your MCP servers
Register each server by URL. Eisoptric discovers its tools, handles OAuth where needed, and seals the credentials in its vault.
Eisoptric MCP · A tool from Eisoptric’s research
Eisoptric MCP is the MCP server your agents talk to. Behind it sit your real MCP servers — CRM, payments, databases, cloud consoles. Eisoptric exposes only the tools you approve, evaluates every call against policy, pauses the sensitive ones for a human, and records everything.
Standards-compliant MCP over HTTP. Works with Claude, ChatGPT, Cursor, Eisoptric Workbench, or any MCP client.
policy Payments v3 production rule payments.transfer when amount > 1000 AND currency == "USD" decision approval_required rule payments.transfer when true decision allow rule db.drop_table when true decision deny
A policy as the engine evaluates it. Conditions are matched against the arguments of each call.
No SDK, no agent code changes. Eisoptric works at the protocol level.
Register each server by URL. Eisoptric discovers its tools, handles OAuth where needed, and seals the credentials in its vault.
Pick the tools each agent should have — across servers. Mark any tool as Call (automatic) or Approval (needs a person).
Add rules with conditions on arguments. Decide per rule: allow, approval required, or deny. Policies are versioned.
Give every agent the same Eisoptric MCP endpoint. They sign in with OAuth and see only their tool set.
Four examples of agents that are useful precisely because they are governed.
Finance operations
The finance agent reconciles invoices and triggers payments through the payments MCP server. Small transfers run automatically. Anything above the threshold waits for a reviewer, who sees the amount, the recipient, and the invoice reference before approving.
Customer support
The support agent gets a tool set with CRM lookup, ticket updates, and email reply. Destructive CRM tools are not in the set, so for this agent they do not exist. Emails to external domains require approval; internal notes go straight through.
Platform and DevOps
The release agent runs rollouts through your deployment MCP server. Staging is automatic. Production rollouts pause for an on-call engineer. Schema-destroying operations are denied outright, regardless of environment.
Data and analytics
Each team gets analyst agents with read-only warehouse tools. Server mapping decides which teams may attach the warehouse at all. Editors are scoped to their own agents, and every query is attributed to the person the agent acted for.
Everything between the agent’s request and your upstream server.
OAuth 2.1 with PKCE for every agent. Each session is bound to a user or an organization; the profile is checked on every request.
Register MCP servers by URL. Eisoptric discovers tools, keeps the catalog current, and manages upstream OAuth and token refresh.
Curated tools per agent, across servers. Only those tools appear in tools/list. Each tool is Call or Approval.
Ordered, versioned rules with conditions on arguments. Every call records the policy id, version, and matched rule.
Sensitive calls wait for one reviewer or a group quorum. The agent resumes with gatewayRunId. Approvals expire.
Upstream tokens and secrets sealed with ML-KEM-1024 and AES-256-GCM. Agents never see them; every read is audited.
Governance events stay searchable. Stored audit payloads use zero-access encryption and open only in a member’s browser, while the gateway processes plaintext in flight.
Approval granted, rejected, and expired are signed with HMAC-SHA256. A successful delivery does not execute the tool.
An agent can never obtain more than the result of an authorized call. These are the mechanisms behind that guarantee.
Access tokens, refresh tokens, and client secrets are sealed individually with ML-KEM-1024 key encapsulation and AES-256-GCM, keys derived via HKDF-SHA384. The key seed lives in configuration, never in the database.
Console and client APIs report whether a secret exists — never its value. Every secret read generates a credential_accessed audit event.
Eisoptric discovers the authorization server, performs dynamic client registration where supported, uses PKCE, and refreshes tokens automatically when an upstream returns 401.
Upstream URLs must use HTTPS (or HTTP on localhost). Private, link-local, and cloud metadata addresses are refused.
A denied call never leaves Eisoptric. A held call returns approval_required with a reference id. A paused agent cannot start a call.
Four console resources, three access levels each. Preset roles admin, operator, viewer, or custom sets. Editors can be scoped to specific agents.
API gateways govern services. Eisoptric governs agents — a caller that reasons, chooses tools, and needs to be stopped sometimes.
Eisoptric Console gives security, platform, and operations teams a shared view of what agents can do and what they have done.
Active agents, pending approvals, recent denials, and spend at a glance.
Register agents, assign tool sets, pause or resume, and scope who may edit them.
Connect MCP servers, review discovered tools, and build tool sets.
Author and version rules; see which policy decided each call.
Approve or reject a call. Multi-approver tasks wait until every required group is done.
Approved tasks wait on their own page until the agent calls the tool again with gatewayRunId.
Search governance events. Raw requests and responses open only in an authorized member’s browser.
Signed notices for approval granted, rejected, and expired. Delivery does not execute the tool.
Members, roles, custom permissions, and MCP server mapping per employee.
Create a free account, connect a server, and write one rule. The first approval request shows you the whole path.