--- title: "Socket MCP server for AI agents - actionlake" description: "Give Claude 107 Socket actions through one MCP server: full scans, repo labels, repos. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/socket updated: 2026-10-23 --- Connectors · Identity & security # Socket MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Socket and the rest of your systems. It gives your agent 107 Socket actions (69 reads, 25 writes and 13 that wait for a confirmation) and holds the Socket credential itself, so the agent never does. It paces Socket's limits and records every call. [Connect Socket 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: "socket_dev.organizations.list", intent: "check which Socket account is connected" } # List organizations · read · 1 upstream call ``` - 107 actions in one signed file - 69 read look, never change - 25 write create and update - 13 wait for a yes destructive, confirmed first Set up ## Connect Socket 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 Socket. Bearer token. 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_key` Socket organization API token (Socket dashboard > Settings > API Tokens) ``` account { op: "connections.requirements", service: "socket_dev" } # 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: "socket_dev.organizations.list" } # list organizations · read · 1 upstream call check { action: "socket_dev.alert_policies.create", input: { … } } # free: inputs, permissions, cost and confirmations, nothing sent ``` Socket at a glance **Sign-in** Bearer token. 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_key` **Limits we pace to** 5 calls a second, per connection **API covered** Socket API v0 (OpenAPI 3.0.0) and v1 (OpenAPI 3.1.0)`api.socket.dev` **Built from** Socket's documentation, read 23 October 2026[api.socket.dev](https://api.socket.dev/v0/openapi) [api.socket.dev](https://api.socket.dev/v1/openapi) [docs.socket.dev](https://docs.socket.dev/reference) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 62 of 69 reads, for up to 5 minutes; a write clears what it affects **Shared entities** 3, so ask can line Socket up with your other systems **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in Socket. 107 actions in 39 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **69** read look, never change - **25** write create and update - **13** destructive wait for a confirmation 1. ### Full scans 9 7 read · 1 write · 1 destructive List full scans · Delete full scan · Rescan full scan · Diff Full Scans 2. ### Repo labels 7 2 read · 4 write · 1 destructive Create repository label (beta) · List repository labels (beta) · Associate repository label (beta) · Disassociate repository label (beta) 3. ### Repos 6 3 read · 2 write · 1 destructive List repositories · Create repository · Get repository · Update repository 4. ### Alert policies 5 2 read · 2 write · 1 destructive List Org Alert Policies · Create Org Alert Policy · Get Org Alert Policy · Update Org Alert Policy 5. ### Alert policy rules 5 2 read · 2 write · 1 destructive Create Org Alert Policy Rule · List Org Alert Policy Rules · Get Org Alert Policy Rule · Update Org Alert Policy Rule 6. ### API tokens 5 1 read · 2 write · 2 destructive Create API Token · List API Tokens · Update API Token · Revoke API Token 7. ### Diff scans 5 3 read · 1 write · 1 destructive Create diff scan from full scan IDs · List diff scans · Get diff scan · SCM Comment for Diff Scan 8. ### Webhooks 5 2 read · 2 write · 1 destructive Create a webhook · List all webhooks · Update webhook · Get webhook **31 more areas · 60 actions** - Alert resolutions **4** - License policy **4** - Reports **4** - Alert triage **3** - Packages **3** - Repo label settings **3** - Threat campaigns **3** - Alert policy migration **2** - Alerts **2** - Analytics **2** - Events **2** - Fix computations **2** - Historical alerts **2** - Historical snapshots **2** - NPM packages **2** - Openapi **2** - Security policy **2** - Telemetry config **2** - Threat feed **2** - Alert types **1** - Audit log **1** - Dependencies **1** - Fixes **1** - Historical dependencies **1** - Integration events **1** - License metadata **1** - Organizations **1** - Quota **1** - Settings **1** - Socket basics **1** - Supported files **1** Top actions ## The Socket API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 23 of Socket's 23 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `socket_dev.alert_policies.list` List Org Alert Policies | List Org Alert Policies. | read | `security.policy.list` 36 connectors | | `socket_dev.alert_policies.create` Create Org Alert Policy | Create Org Alert Policy. | write | `security.policy.create` 25 connectors | | `socket_dev.alerts.list` List latest alerts (Beta) | List latest alerts (Beta). | read | `security.alert.list` 22 connectors | | `socket_dev.repos.list` List repositories | List repositories. | read | `devops.repository.list` 28 connectors | | `socket_dev.audit_log.list` Get Audit Log Events | Get Audit Log Events. | read | `security.audit_log.list` 69 connectors | | `socket_dev.alert_policies.delete` Delete Org Alert Policy | Delete Org Alert Policy. | destructive | `security.policy.delete` 21 connectors | | `socket_dev.repos.create` Create repository | Create repository. | write | `devops.repository.create` 18 connectors | | `socket_dev.webhooks.create` Create a webhook | Create a webhook. | write | `automation.webhook.create` 209 connectors | | `socket_dev.webhooks.list` List all webhooks | List all webhooks. | read | `automation.webhook.list` 202 connectors | | `socket_dev.threat_feed.list` Get Threat Feed Items (Beta) | Get Threat Feed Items (Beta). | read | `security.threat.list` 7 connectors | | `socket_dev.api_tokens.create` Create API Token | Create API Token. | write | `identity.api_key.create` 100 connectors | | `socket_dev.api_tokens.list` List API Tokens | List API Tokens. | read | `identity.api_key.list` 96 connectors | Try it ## Prompts to paste into Claude. Each one names the Socket actions it will call, so you know what it reads and what it changes before you send it. 1. Read read Which Socket alerts are open right now? Group them by service. calls `socket_dev.alerts.list` 2. Write write Create Org Alert Policy in Socket. Show me exactly what you will send before you save it. calls `socket_dev.alert_policies.create` Governance for Socket ## Destructive actions wait for a yes. 13 Socket actions are destructive. These are all of them: - Delete Org Alert Policy `socket_dev.alert_policies.delete` - Delete repository `socket_dev.repos.delete` - Delete webhook `socket_dev.webhooks.delete` - Delete full scan `socket_dev.full_scans.delete` - Delete a report `socket_dev.reports.delete` - Revoke API Token `socket_dev.api_tokens.revoke` - Rotate API Token `socket_dev.api_tokens.rotate` - Delete diff scan `socket_dev.diff_scans.delete` - Delete repository label (beta) `socket_dev.repo_labels.delete` - Delete Org Alert Triage `socket_dev.alert_triage.delete` - Delete Org Alert Resolution `socket_dev.alert_resolutions.delete` - Delete Org Alert Policy Rule `socket_dev.alert_policy_rules.delete` - Delete repository label setting (beta) `socket_dev.repo_label_settings.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 socket_dev.alert_policies.delete confirm_policy: **human** Delete Org Alert Policy? **intent:** the user asked me to delete Org Alert Policy run suspended · waiting for a named person · key _socket-dev-agent_ cannot confirm itself In the console, or from an emailed signed link. a key for this connector ``` account { op: "keys.create", name: "socket-dev-agent", allowed_actions: ["socket_dev.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "socket_dev.alert_policies.delete", approver: "lead@example.com" }, { match: "socket_dev.repos.delete", approver: "lead@example.com" }, { match: "socket_dev.webhooks.delete", approver: "lead@example.com" } ] } ``` Illustrative. Scoped to Socket only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person. Cost ## What Socket costs on actionlake. Every Socket action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call Socket 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 107 Socket actions - 107 actions page each page of a long list is one call - 62 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 Socket action. 107 actions by area: the id your agent calls, what it does, and its effect. **Full scans 9** - `socket_dev.full_scans.delete` Delete full scan destructive - `socket_dev.full_scans.diff` Diff Full Scans read - `socket_dev.full_scans.diff_gfm` SCM Comment for Scan Diff read - `socket_dev.full_scans.export_cyclonedx` Export CycloneDX SBOM (Beta) read - `socket_dev.full_scans.export_openvex` Export OpenVEX Document (Beta) read - `socket_dev.full_scans.export_spdx` Export SPDX SBOM (Beta) read - `socket_dev.full_scans.get_metadata` Get full scan metadata read - `socket_dev.full_scans.list` List full scans read - `socket_dev.full_scans.rescan` Rescan full scan write **Repo labels 7** - `socket_dev.repo_labels.associate` Associate repository label (beta) write - `socket_dev.repo_labels.create` Create repository label (beta) write - `socket_dev.repo_labels.delete` Delete repository label (beta) destructive - `socket_dev.repo_labels.disassociate` Disassociate repository label (beta) write - `socket_dev.repo_labels.get` Get repository label (beta) read - `socket_dev.repo_labels.list` List repository labels (beta) read - `socket_dev.repo_labels.update` Update repository label (beta) write **Repos 6** - `socket_dev.repos.create` Create repository write - `socket_dev.repos.delete` Delete repository destructive - `socket_dev.repos.get` Get repository read - `socket_dev.repos.list` List repositories read - `socket_dev.repos.list_legacy` List GitHub repositories read - `socket_dev.repos.update` Update repository write **Alert policies 5** - `socket_dev.alert_policies.create` Create Org Alert Policy write - `socket_dev.alert_policies.delete` Delete Org Alert Policy destructive - `socket_dev.alert_policies.get` Get Org Alert Policy read - `socket_dev.alert_policies.list` List Org Alert Policies read - `socket_dev.alert_policies.update` Update Org Alert Policy write **Alert policy rules 5** - `socket_dev.alert_policy_rules.create` Create Org Alert Policy Rule write - `socket_dev.alert_policy_rules.delete` Delete Org Alert Policy Rule destructive - `socket_dev.alert_policy_rules.get` Get Org Alert Policy Rule read - `socket_dev.alert_policy_rules.list` List Org Alert Policy Rules read - `socket_dev.alert_policy_rules.update` Update Org Alert Policy Rule write **API tokens 5** - `socket_dev.api_tokens.create` Create API Token write - `socket_dev.api_tokens.list` List API Tokens read - `socket_dev.api_tokens.revoke` Revoke API Token destructive - `socket_dev.api_tokens.rotate` Rotate API Token destructive - `socket_dev.api_tokens.update` Update API Token write **Diff scans 5** - `socket_dev.diff_scans.create_from_ids` Create diff scan from full scan IDs write - `socket_dev.diff_scans.delete` Delete diff scan destructive - `socket_dev.diff_scans.get` Get diff scan read - `socket_dev.diff_scans.get_gfm` SCM Comment for Diff Scan read - `socket_dev.diff_scans.list` List diff scans read **Webhooks 5** - `socket_dev.webhooks.create` Create a webhook write - `socket_dev.webhooks.delete` Delete webhook destructive - `socket_dev.webhooks.get` Get webhook read - `socket_dev.webhooks.list` List all webhooks read - `socket_dev.webhooks.update` Update webhook write **Alert resolutions 4** - `socket_dev.alert_resolutions.create` Create Org Alert Resolution write - `socket_dev.alert_resolutions.delete` Delete Org Alert Resolution destructive - `socket_dev.alert_resolutions.get` Get Org Alert Resolution read - `socket_dev.alert_resolutions.list` List Org Alert Resolutions read **License policy 4** - `socket_dev.license_policy.get` Get Organization License Policy read - `socket_dev.license_policy.saturate` Saturate License Policy (Legacy) read - `socket_dev.license_policy.update` Update License Policy write - `socket_dev.license_policy.view` Get License Policy (Beta) read **Reports 4** - `socket_dev.reports.delete` Delete a report destructive - `socket_dev.reports.get` View a report read - `socket_dev.reports.get_supported_files` Get supported files for report read - `socket_dev.reports.list` Get list of reports read **Alert triage 3** - `socket_dev.alert_triage.delete` Delete Org Alert Triage destructive - `socket_dev.alert_triage.list` List Org Alert Triage read - `socket_dev.alert_triage.update` Create/Update Org Alert Triage write **Packages 3** - `socket_dev.packages.check` Evaluate package versions against organization policy read - `socket_dev.packages.list_versions` List published versions for a package by PURL read - `socket_dev.packages.summarize` Summarize package intelligence and findings read **Repo label settings 3** - `socket_dev.repo_label_settings.delete` Delete repository label setting (beta) destructive - `socket_dev.repo_label_settings.get` Get repository label setting (beta) read - `socket_dev.repo_label_settings.update` Update repository label setting (beta) write **Threat campaigns 3** - `socket_dev.threat_campaigns.get` Get a threat campaign read - `socket_dev.threat_campaigns.list` List threat campaigns read - `socket_dev.threat_campaigns.list_packages` List packages for a threat campaign read **Alert policy migration 2** - `socket_dev.alert_policy_migration.get_status` Get Org Alert Policy Migration Status read - `socket_dev.alert_policy_migration.translate` Translate Org Alert Triage read **Alerts 2** - `socket_dev.alerts.list` List latest alerts (Beta) read - `socket_dev.alerts.list_full_scans` List full scans associated with alert (Beta) read **Analytics 2** - `socket_dev.analytics.get_org` Get organization analytics (unstable) read - `socket_dev.analytics.get_repo` Get repository analytics read **Events 2** - `socket_dev.events.create` Post organization events write - `socket_dev.events.list` List organization events read **Fix computations 2** - `socket_dev.fix_computations.create` Start fix computation write - `socket_dev.fix_computations.get` Get fix computation read **Historical alerts 2** - `socket_dev.historical_alerts.list` List historical alerts (Beta) read - `socket_dev.historical_alerts.trend` Trend of historical alerts (Beta) read **Historical snapshots 2** - `socket_dev.historical_snapshots.create` Start historical data snapshot job (Beta) write - `socket_dev.historical_snapshots.list` List details of periodic historical data snapshots (Beta) read **NPM packages 2** - `socket_dev.npm_packages.get_issues` Get issues by package read - `socket_dev.npm_packages.get_score` Get score by package read **Openapi 2** - `socket_dev.openapi.get` Returns the OpenAPI definition read - `socket_dev.openapi.get_v1` Returns the OpenAPI definition read **Security policy 2** - `socket_dev.security_policy.get` Get Organization Security Policy read - `socket_dev.security_policy.update` Update Security Policy write **Telemetry config 2** - `socket_dev.telemetry_config.get` Get Organization Telemetry Config read - `socket_dev.telemetry_config.update` Update Telemetry Config write **Threat feed 2** - `socket_dev.threat_feed.list` Get Threat Feed Items (Beta) read - `socket_dev.threat_feed.list_legacy` Get Threat Feed Items (Deprecated) read **Alert types 1** - `socket_dev.alert_types.query` Alert Types Metadata read **Audit log 1** - `socket_dev.audit_log.list` Get Audit Log Events read **Dependencies 1** - `socket_dev.dependencies.search` Search dependencies read **Fixes 1** - `socket_dev.fixes.get` Fetch fixes for vulnerabilities in a repository, scan, or uploaded manifest read **Historical dependencies 1** - `socket_dev.historical_dependencies.trend` Trend of historical dependencies (Beta) read **Integration events 1** - `socket_dev.integration_events.list` Get integration events read **License metadata 1** - `socket_dev.license_metadata.query` License Metadata read **Organizations 1** - `socket_dev.organizations.list` List organizations read **Quota 1** - `socket_dev.quota.get` Get quota read **Settings 1** - `socket_dev.settings.query` Calculate settings read **Socket basics 1** - `socket_dev.socket_basics.get` Get Socket Basics configuration, including toggles for the various tools it supports. read **Supported files 1** - `socket_dev.supported_files.get` Get supported file types read Questions ## The Socket MCP server, answered. **Is there a Socket MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 107 Socket actions across full scans, repo labels, repos and alert policies, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Socket. **What do I need to connect Socket?** Socket organization API token (Socket dashboard > Settings > API Tokens). The free call account { op: "connections.requirements", service: "socket_dev" } lists exactly what to paste. **Can an AI agent delete or change things in Socket?** Only if its key allows it, and only with an explicit confirmation. 13 Socket actions are destructive, including delete Org Alert Policy, delete repository and delete webhook. 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 Socket API limit?** actionlake paces every call to the limits in the Socket service file: 5 calls a second per connection. Repeated reads are answered from cache (62 Socket actions can be), which never reaches Socket. **What does a Socket action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (107 Socket actions page). Cache hits, searches, dry runs and calls Socket 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 Socket API does it cover?** The Socket API v0 (OpenAPI 3.0.0) and v1 (OpenAPI 3.1.0) at api.socket.dev. It is built from Socket's documentation as read on 23 October 2026. 107 actions in 39 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my Socket 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 Socket 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 Socket Shares the most action names with - [ProjectDiscovery Cloud 8](https://actionlake.com/connectors/projectdiscovery-cloud) - [Panther 8](https://actionlake.com/connectors/panther) - [SonarQube Cloud 7](https://actionlake.com/connectors/sonarqube-cloud) - [Palo Alto Networks Strata Cloud Manager / Prisma Access 5](https://actionlake.com/connectors/palo-alto-networks-strata-cloud-manager-prisma-access) - [VMware Carbon Black Cloud 5](https://actionlake.com/connectors/vmware-carbon-black-cloud) - [Palo Alto Networks Cortex XDR 5](https://actionlake.com/connectors/palo-alto-networks-cortex-xdr) Joins with, on shared entities - [Sophos Central 2](https://actionlake.com/connectors/sophos-central) - [Microsoft Defender for Cloud 2](https://actionlake.com/connectors/microsoft-defender-for-cloud) - [Sentry 2](https://actionlake.com/connectors/sentry) - [NinjaOne 1](https://actionlake.com/connectors/ninjaone) - [Fortinet FortiGate 1](https://actionlake.com/connectors/fortinet-fortigate) - [Harness Platform 1](https://actionlake.com/connectors/harness-platform) Browse - [All Identity & security connectors](https://actionlake.com/connectors/category/identity-and-security) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by Socket; the name is the vendor's own. Counts are from the Socket service file, version 1.0.0. ## Give your agent Socket today. [Connect Socket 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/socket More: https://actionlake.com/llms.txt