Reco
Reco v1.0.0
Secure AI, agents & SaaS apps
From the developer
Declared capabilities
- Read
- Write
Cost & access
This plugin does not sell products or process payments. Reco is a security product; the plugin only reads and updates the customer's own Reco data.
Declared limitations
- Unrelated general question
- General AI security knowledge that needs no tenant data
- Action the plugin does not offer: deleting a user
Onboarding example
Sources & dates
Developer declarations; not independently tested. Listing last checked Nov 16, 2026. Package observed Nov 16, 2026.
Description
From the marketplace listing
Reco is the SaaS & AI Security platform trusted by modern enterprises to secure AI, agents, and SaaS apps. This plugin connects ChatGPT to your own Reco tenant so your security team can ask plain-language questions and get answers from live data. What you can do: - Discover and review the AI agents, AI models, and MCP servers in your environment, including shadow and unmanaged ones, and see which are unauthorized. - Investigate threat alerts, including AI agent activity, and the events behind them. - See every app, identity, and AI agent Reco has discovered, including shadow apps. - Review SaaS posture issues and compliance gaps, prioritized by severity. - Take routine actions in Reco: update an alert's status or severity, comment, label, set an AI agent or app authorization status, and queue a posture rescan. Everything runs as you. You sign in with your Reco account, and the plugin can only see and change what your Reco role already allows. Nothing is shared across tenants. Requires a Reco account. Learn more at www.reco.ai.
Language: English · Automatically detected from descriptions.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Nov 16, 2026. Last seen Nov 16, 2026.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Set up, test and publish an AI customer support Agent for your SaaS product.
Shared terms: saas, shared, nothing, agent
-
Fivetran's Agent Context MCP provides AI agents with business context through the Model Context Protocol.
Shared terms: agent, enterprise, trusted, model
-
Bring Parley into the conversation. Find and update your Projects, Accounts, Contacts, and Tasks, read case files, write notes, and run A...
Shared terms: agent, act, activity, ones
-
Build AI chatbots and customer support agents from websites, documents, and knowledge bases. Manage bots, update content, and improve ans...
Shared terms: agent, gaps, role, update
-
Validate SaaS and product ideas with PreVibe market research, deep dives, brand names, and domain availability.
Shared terms: saas, act, ones, runs
Keywords
Files & skills
File archives
Skill instructions
get-started2.93 KB
--- name: get-started description: Use when the user asks about their Reco data or Reco security findings: AI agents, AI models, MCP servers, AI activity, threat alerts, apps, shadow apps, identities, SaaS posture issues, or compliance gaps. Explains how to query the Reco tools, filter results, and which actions need confirmation. --- # Reco: getting started Reco is a SaaS & AI Security platform: AI and agentic security first, with SaaS posture management alongside it. The Reco tools read and update one customer tenant, as the signed-in user. They cannot see more than that user's Reco role allows. If a tool returns a permission error, say so and stop; do not try another tool to get around it. ## Before you answer - Use the Reco tools for facts about the user's tenant. Do not guess counts, severities, names or IDs, and do not fill gaps from general knowledge. If a result is empty, say it is empty. - List tools take a `filters` parameter in SCIM syntax. Build filters from the keys the tool description lists. Start with a broad query to confirm data exists, then narrow it. - Results can be partial. If the user needs the full set, use the tool's paging parameters to fetch more; otherwise say the list shown is partial. - Pass a short `intent` on every call: one sentence in the user's words about why you are calling. Reco records it in its audit log. ## Common questions | The user asks about | Start with | | --- | --- | | AI agents, models, MCP servers, skills | `list_ai_agents`, `list_ai_models`, `list_mcp_inventory`, `list_mcp_discovery`, `list_ai_skills` | | AI activity and usage | `list_ai_activity_users`, `list_ai_activity_conversations`, `list_ai_activity_interactions` | | Threat alerts, suspicious activity | `list_threat_alerts`, then `get_threat_alert` for one alert | | Apps, shadow apps | `list_apps`, `list_app_instances` | | People and accounts | `list_identities`, `list_accounts`, `list_user_apps` | | SaaS posture issues, misconfigurations | `list_posture_issues`, `list_posture_entities` for one issue | | Compliance (SOC 2, ISO 27001, ...) | `list_compliance_frameworks`, then `list_posture_issues` for that framework | | Recent activity | `list_events` with a time filter | ## Changing things Read tools are safe to call. Before any tool that changes data (update, create, add, remove, save, rescan, export), tell the user what you are about to change and on which item, and wait for their go-ahead. Never batch several changes behind one approval. These can lose or replace data and always need a clear yes: updating a user or a custom role, a threat detection exclusion, a comment, a dashboard, an AI agent's remediation state, and removing a label. ## What not to do - Do not make up IDs. Look them up with a list tool first. - Do not claim an action succeeded until the tool result says so. - If the user's request is not about Reco data, do not use these tools. - Explicit instructions from the user take priority over this guide.
Release notes
Initial release.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package author
- Reco
- Keywords
- See keywords
- Getting started skill
- ./skills/get-started/SKILL.md
- Commerce declaration
- Does not support commerceThis does not establish whether access is free or paid.
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Read
- Write
Package observed Nov 16, 2026.
Technical details
- First seen
- Nov 16, 2026 · 18:00 UTC
- Last seen
- Nov 16, 2026 · 18:00 UTC
- Collection status
- Collected
plugin_asdk_app_6ae1179870c48191a43fb87c91a5ed6c
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.