{"id":"ai.hiddencontent/mcp","slug":"ai-hiddencontent-mcp","title":"HiddenContent","description":"Check a document for hidden text before your agent reads it. PDF, Office, RTF, HTML.","version":"0.4.18","publisher":{"kind":"domain","id":"hiddencontent.ai","label":"hiddencontent.ai","url":"https://hiddencontent.ai"},"website":"https://hiddencontent.ai/start?ref=mcp-registry","repository":"https://github.com/AeroSpark-ai/hiddencontent-mcp","remotes":[{"type":"streamable-http","url":"https://api.hiddencontent.ai/v1/mcp"}],"packages":[{"registryType":"npm","identifier":"@hiddencontent/mcp","version":"0.4.18","transport":{"type":"stdio"},"environmentVariables":[{"description":"API token for the HiddenContent service. Get one at https://hiddencontent.ai/start?ref=mcp-registry — the server refuses to start without it and says so.","isRequired":true,"isSecret":true,"name":"HCS_API_TOKEN"},{"description":"Base URL of the service. Defaults to the hosted API; set it only when pointing at a self-hosted instance.","name":"HCS_URL"},{"description":"Comma-separated list of what your agent can actually do. The only accepted values are `tool-use`, `network-egress` and `code-execution`. These turn on the checks for concealed text that instructs a model to call a tool, send data or run code — declaring more can raise severity and never lowers it, and declaring nothing leaves those checks inert. Defaults to `tool-use` in the bundle install.","name":"HCS_CAPABILITIES"}]},{"registryType":"mcpb","identifier":"https://github.com/AeroSpark-ai/hiddencontent-mcp/releases/download/v0.4.18/hiddencontent.mcpb","fileSha256":"c5d05fc248950e6eac597c3f4e9910e2521425ce61ad39e32f4f1f3f80d61f5f","transport":{"type":"stdio"},"environmentVariables":[{"description":"API token for the HiddenContent service. Get one at https://hiddencontent.ai/start?ref=mcp-registry — the server refuses to start without it and says so.","isRequired":true,"isSecret":true,"name":"HCS_API_TOKEN"},{"description":"Base URL of the service. Defaults to the hosted API; set it only when pointing at a self-hosted instance.","name":"HCS_URL"},{"description":"Comma-separated list of what your agent can actually do. The only accepted values are `tool-use`, `network-egress` and `code-execution`. These turn on the checks for concealed text that instructs a model to call a tool, send data or run code — declaring more can raise severity and never lowers it, and declaring nothing leaves those checks inert. Defaults to `tool-use` in the bundle install.","name":"HCS_CAPABILITIES"}]}],"published":"2026-11-13","updated":"2026-11-13","status":"auth","auth":"oauth","latency_ms":904,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[],"server_info":{},"category":"productivity","tags":["agents"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":92,"indexable":true,"first_seen":"2026-09-01","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/ai-hiddencontent-mcp/"}