--- title: "Material Security MCP server for AI agents - actionlake" description: "Give Claude 31 Material Security actions through one MCP server: trusted entities, accounts. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/material-security updated: 2026-10-23 --- Connectors · MSP & PSA # Material Security MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Material Security and the rest of your systems. It gives your agent 31 Material Security actions (19 reads, 9 writes and 3 that wait for a confirmation) and holds the Material Security credential itself, so the agent never does. It paces Material Security's limits and records every call. [Connect Material Security free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) 100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you. `claude mcp add --transport http actionlake https://connect.actionlake.com/mcp` the first call ``` do { action: "material_security.accounts.list", intent: "check which Material Security account is connected" } # List Accounts · read · 1 upstream call ``` - 31 actions in one signed file - 19 read look, never change - 9 write create and update - 3 wait for a yes destructive, confirmed first Set up ## Connect Material Security in three steps. 1. 01 ### Add actionlake to Claude. Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us. `https://connect.actionlake.com/mcp` 2. 02 ### Connect Material Security. API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key. - `api_token` Material Security API token - `host` Where your Material Security lives: your host ``` account { op: "connections.requirements", service: "material_security" } # free: exactly what to paste, and what is found for you ``` 3. 03 ### Make the first call. Check before a write. Ask in plain words; Claude picks the action. Before anything changes, `check` validates the call and prices it, for free. ``` do { action: "material_security.accounts.list" } # list accounts · read · 1 upstream call check { action: "material_security.accounts.update", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Material Security at a glance **Sign-in** API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. **You provide** `api_token` **Setup fields** `host` **Limits we pace to** 300 calls a minute, per connection **API covered** Material Security API v1 (OpenAPI 3.1, current release), at your Material Security instance's API base URL, which you enter when connecting **Built from** Material Security's documentation, read 23 October 2026[openapi.gitbook.com](https://openapi.gitbook.com/o/xxHB3fU1iXYTy26adOT3/spec/api-v1-current-release.json) [docs.material.security](https://docs.material.security/reference/api-v1) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 17 of 19 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 5, so ask can line Material Security up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Material Security. 31 actions in 11 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **19** read look, never change - **9** write create and update - **3** destructive wait for a confirmation 1. ### Trusted entities 6 2 read · 2 write · 2 destructive Create Trusted Entity · List Trusted Entities · Get Trusted Entity · Update Trusted Entity 2. ### Accounts 4 2 read · 2 write · 0 destructive List Accounts · Get Account · Update Account · Bulk Accounts 3. ### Groups 4 2 read · 2 write · 0 destructive List Groups · Get Group · Update Group · Bulk Groups 4. ### Messages 4 3 read · 1 write · 0 destructive Search Messages · Get Message Search Results · Get Message · Move Messages to Inbox 5. ### Issues 3 2 read · 1 write · 0 destructive List Issues · Get Issue · Update Issue 6. ### Oauth apps 3 2 read · 1 write · 0 destructive List OAuth Apps · Get OAuth App · Update OAuth App 7. ### Oauth app accounts 2 1 read · 0 write · 1 destructive Revoke OAuth App Account Grant · List OAuth App Accounts 8. ### Tenants 2 2 read · 0 write · 0 destructive List Tenants · Get Tenant **3 more areas · 3 actions** - Group members **1** - Issue messages **1** - Roles **1** Top actions ## The Material Security API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 14 of Material Security's 14 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `material_security.accounts.list` List Accounts | List Accounts. | read | `identity.user.list` 474 connectors | | `material_security.groups.list` List Groups | List Groups. | read | `identity.group.list` 262 connectors | | `material_security.roles.list` List Roles | List Roles. | read | `identity.role.list` 184 connectors | | `material_security.oauth_apps.list` List OAuth Apps | List OAuth Apps. | read | `identity.application.list` 37 connectors | | `material_security.accounts.get` Get Account | Get Account. | read | `identity.user.get` 399 connectors | | `material_security.accounts.update` Update Account | Update Account. | write | `identity.user.update` 280 connectors | | `material_security.groups.get` Get Group | Get Group. | read | `identity.group.get` 212 connectors | | `material_security.groups.update` Update Group | Update Group. | write | `identity.group.update` 189 connectors | | `material_security.oauth_apps.get` Get OAuth App | Get OAuth App. | read | `identity.application.get` 33 connectors | | `material_security.group_members.list` List Group Members | List Group Members. | read | `identity.group_member.list` 103 connectors | | `material_security.oauth_apps.update` Update OAuth App | Update OAuth App. | write | `identity.application.update` 24 connectors | | `material_security.oauth_app_accounts.revoke` Revoke OAuth App Account Grant | Revoke OAuth App Account Grant. | destructive | `identity.application_grant.revoke` 4 connectors | Try it ## Prompts to paste into Claude. Each one names the Material Security actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Who has access in Material Security? List every user and their role. calls `material_security.accounts.list` 2. Write write Update Account in Material Security. Show me exactly what you will send before you save it. calls `material_security.accounts.update` Governance for Material Security ## Destructive actions wait for a yes. 3 Material Security actions are destructive. These are all of them: - Revoke OAuth App Account Grant `material_security.oauth_app_accounts.revoke` - Bulk Trusted Entities `material_security.trusted_entities.bulk` - Delete Trusted Entity `material_security.trusted_entities.delete` A destructive action runs only with `confirm: true`. Under the `human` policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after. do material_security.trusted_entities.delete confirm_policy: **human** Delete Trusted Entity? **intent:** the user asked me to delete Trusted Entity run suspended · waiting for a named person · key _material-security-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "material-security-agent", allowed_actions: ["material_security.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "material_security.oauth_app_accounts.revoke", approver: "lead@example.com" }, { match: "material_security.trusted_entities.bulk", approver: "lead@example.com" }, { match: "material_security.trusted_entities.delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Material Security only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Material Security costs on actionlake. Every Material Security action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Material Security refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. - 1 upstream call per action all 31 Material Security actions - 31 actions page each page of a long list is one call - 17 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every Material Security action. 31 actions by area: the id your agent calls, what it does, and its effect. **Trusted entities 6** - `material_security.trusted_entities.bulk` Bulk Trusted Entities destructive - `material_security.trusted_entities.create` Create Trusted Entity write - `material_security.trusted_entities.delete` Delete Trusted Entity destructive - `material_security.trusted_entities.get` Get Trusted Entity read - `material_security.trusted_entities.list` List Trusted Entities read - `material_security.trusted_entities.update` Update Trusted Entity write **Accounts 4** - `material_security.accounts.bulk_update` Bulk Accounts write - `material_security.accounts.get` Get Account read - `material_security.accounts.list` List Accounts read - `material_security.accounts.update` Update Account write **Groups 4** - `material_security.groups.bulk_update` Bulk Groups write - `material_security.groups.get` Get Group read - `material_security.groups.list` List Groups read - `material_security.groups.update` Update Group write **Messages 4** - `material_security.messages.get` Get Message read - `material_security.messages.move_to_inbox` Move Messages to Inbox write - `material_security.messages.search` Search Messages read - `material_security.messages.search_results` Get Message Search Results read **Issues 3** - `material_security.issues.get` Get Issue read - `material_security.issues.list` List Issues read - `material_security.issues.update` Update Issue write **Oauth apps 3** - `material_security.oauth_apps.get` Get OAuth App read - `material_security.oauth_apps.list` List OAuth Apps read - `material_security.oauth_apps.update` Update OAuth App write **Oauth app accounts 2** - `material_security.oauth_app_accounts.list` List OAuth App Accounts read - `material_security.oauth_app_accounts.revoke` Revoke OAuth App Account Grant destructive **Tenants 2** - `material_security.tenants.get` Get Tenant read - `material_security.tenants.list` List Tenants read **Group members 1** - `material_security.group_members.list` List Group Members read **Issue messages 1** - `material_security.issue_messages.list` List Issue Messages read **Roles 1** - `material_security.roles.list` List Roles read Questions ## The Material Security MCP server, answered. **Is there a Material Security MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 31 Material Security actions across trusted entities, accounts, groups and messages, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Material Security. **What do I need to connect Material Security?** Material Security API token. Plus your host. The free call account { op: "connections.requirements", service: "material_security" } lists exactly what to paste. **Can an AI agent delete or change things in Material Security?** Only if its key allows it, and only with an explicit confirmation. 3 Material Security actions are destructive, including revoke OAuth App Account Grant, bulk Trusted Entities and delete Trusted Entity. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it. **Will an AI agent use up my Material Security API limit?** actionlake paces every call to the limits in the Material Security service file: 300 calls a minute per connection. Repeated reads are answered from cache (17 Material Security actions can be), which never reaches Material Security. **What does a Material Security action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (31 Material Security actions page). Cache hits, searches, dry runs and calls Material Security refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000. **Which Material Security API does it cover?** The Material Security API v1 (OpenAPI 3.1, current release) at your Material Security instance's API base URL, which you enter when connecting. It is built from Material Security's documentation as read on 23 October 2026. 31 actions in 11 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Material Security data, and where?** actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Material Security credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models. **Which AI clients can use it?** Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names. ## More connectors like Material Security Shares the most action names with - [Delinea Secret Server 8](https://actionlake.com/connectors/delinea-secret-server) - [Commvault Cloud 7](https://actionlake.com/connectors/commvault-cloud) - [Cato Networks SASE 6](https://actionlake.com/connectors/cato-networks-sase) - [3CX 6](https://actionlake.com/connectors/3cx) - [KnowBe4 5](https://actionlake.com/connectors/knowbe4) - [ImmyBot 4](https://actionlake.com/connectors/immybot) Joins with, on shared entities - [Cloudflare 5](https://actionlake.com/connectors/cloudflare) - [JumpCloud 5](https://actionlake.com/connectors/jumpcloud) - [Microsoft 365 Users 4](https://actionlake.com/connectors/microsoft-365-users) - [SailPoint Identity Security Cloud 4](https://actionlake.com/connectors/sailpoint-identity-security-cloud) - [PingOne Platform API 4](https://actionlake.com/connectors/pingone-platform-api) - [Okta 4](https://actionlake.com/connectors/okta) Browse - [All MSP & PSA connectors](https://actionlake.com/connectors/category/msp-and-psa) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Material Security; the name is the vendor's own. Counts are from the Material Security service file, version 1.0.0. ## Give your agent Material Security today. [Connect Material Security free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/material-security More: https://actionlake.com/llms.txt