Plori MCP Server

plori

plori (plori.ai): a cloud AI agent with its own persistent environment - durable disk, real CLI tools, and memory.

plori provides the agent: each one gets a persistent machine with a real disk, real tools, and memory of its own. Idle agents scale to zero. You talk to your agents in the web app, or drive them from your own tools over MCP and REST.

This repository is the integration front door. The product itself lives at plori.ai; the remote MCP server lives at https://api.plori.ai/mcp.

Connect your MCP client

plori is a remote MCP server (streamable HTTP). There is nothing to install or run locally. Sign-in happens in your browser via OAuth 2.1 the first time your client connects; headless environments can use an API key instead.

Claude Code

claude mcp add --transport http plori https://api.plori.ai/mcp

Cursor

Use the one-click Add to Cursor button, or add manually: Settings -> MCP -> Add server with URL https://api.plori.ai/mcp.

VS Code

code --add-mcp '{"name":"plori","type":"http","url":"https://api.plori.ai/mcp"}'

Codex CLI

codex mcp add plori --url https://api.plori.ai/mcp
codex mcp login plori

Codex auto-detects plori's OAuth on login. One-install alternative with the skill bundled: codex plugin marketplace add plori-ai/codex-plugin then codex plugin add plori@plori.

Cline

Follow llms-install.md, written for Cline's automated installer.

Any other client

Native streamable-HTTP clients connect to https://api.plori.ai/mcp directly. Clients that only speak stdio can bridge with the plori-mcp npm package (a thin wrapper around mcp-remote with the endpoint pinned; this repository is its source):

npx plori-mcp
# headless / CI: authenticate with an API key instead of the OAuth flow
npx plori-mcp --header "Authorization: Bearer plori_sk_..."
# equivalent, without the wrapper:
npx mcp-remote https://api.plori.ai/mcp

API keys are minted in Dashboard -> Settings on a registered account.

Or skip MCP: your own terminal

The plori CLI is not an MCP client. It is a door of its own, and it opens the same live session the web app shows: the recent history, a prompt, streaming output, and the approval queue in one place. A turn you send in the terminal appears in an open browser tab as it streams.

curl -fsSL https://plori.ai/install.sh | sh
plori login && plori attach <agent-name>

The installer drops one static binary in ~/.local/bin and needs no Node; if that directory is not on your PATH yet, the script prints the line to add. npm i -g @plori/cli works too. The argument to attach is an agent name, an agent id, or a session id, so a session id copied out of the web app works on its own. Ctrl-D detaches and leaves the run going on the server.

The terminal does not give the agent access to your local files. The shell, the disk, and the files are the agent's own cloud environment.

Verify the connection

Ask your client:

List my plori agents and tell me how many credits I have left.

You should see list_agents and get_credits tool calls and a real answer.

What the tools do

The server exposes 24 tools in five groups:

• Agents: list, inspect, create, and delete agents; pick the model an agent runs.
• Runs: invoke an agent and read its reply (blocking or fire-and-forget), list runs, fetch a past result, or cancel an in-flight run.
• Human-in-the-loop: list an agent's pending questions and answer them.
• Scheduling: schedule a deferred run so an agent works while you are away.
• Workflows: list every workflow or filter by holding agent / the unassigned bucket (list_workflows with optional agent_id UUID or "none"), read one with the step projection pinned for execution (get_workflow) or read an exact version's full definition (get_workflow_version), edit a draft under compare-and-swap (edit_workflow), create one for an agent to build (create_workflow, with optional agent_id), run a built workflow now as a real, billed execution (run_workflow), and read recent execution history (list_workflow_executions) or poll one execution's status, timing, credits, and per-step input/output payloads (get_workflow_execution).

Account reads round out the set: get_credits, get_usage, get_disk, and list_connections — your third-party OAuth providers with status, authorization and expiry times, and the scopes configured for each. Tokens and client secrets are never returned.

Costs: creating and running agents spends plori credits from your account. Reading (lists, results, balances) is free. The pricing page has the details; revoke a client's access any time in your client's settings, or revoke the API key in Dashboard -> Settings.

For AI agents reading this

The machine-readable entry points:

• Front door: plori.ai/agents.md
• Site index: plori.ai/llms.txt
• Skill: SKILL.md (index: /.well-known/agent-skills/index.json)
• MCP server card: https://api.plori.ai/mcp/server-card
• OAuth discovery: RFC 9728 protected-resource metadata on api.plori.ai, dynamic client registration supported
• Registry entry: ai.plori/plori in the official MCP Registry

Every page on plori.ai is also served as Markdown: append .md to the path or send Accept: text/markdown.

Docs and support

• Connect guide (per-client, kept current)
• Docs
• Privacy and terms
• Questions: agent@plori.ai