Tools Guide
Choose which tool providers your agent can use, and check their harness requirements and action namespaces. List the tools currently enabled before adding another.
lnk agent tool listLink's Tools
Link has eight tool providers. Their managed actions use the namespaces below, with availability depending on the harness and enabled grants.
| Tool | What it does |
|---|---|
| Memory | Its files and conversations, searched by meaning |
| Scheduler | Subagents, schedules and messages from others |
| Web | A page as markdown, and a search with your key |
| Browser | A real browser, sandboxed, read and clicked |
| Desktop | A virtual desktop, its mouse, keys and screenshots |
| Run | Programs, each call sandboxed, long ones behind |
| File | Its files read, written and changed |
| Code | What language servers find wrong, and names |
Each tool runs as an MCP server outside your agent's sandbox, and your agent calls it through its proxy. Each tool's page says what it does in full: words and meaning in Memory's search, the browser's own sandbox, the desktop's mouse and keys, Run's background programs.
Give your agent one
lnk agent tool list shows which your agent has, and lnk agent tool add memory, add web, add browser or add desktop gives it one;
its first lnk agent start offers them.
Which harness has which
Memory, Web, Browser and Desktop work in any harness, Scheduler in any harness that reads who a message is from (every harness that comes with Link does), and Run, File and Code in any harness that keeps to the files folder's layout. Today those are Link Harness, since the other harnesses bring files, a shell and code of their own.
Off until you add them
Scheduler, Run, File and Code come with Link Harness, each off until
lnk agent tool add <name> turns it on, or its agent's spec says
[tool.<name>] enabled = true. A tool knows
nothing of a harness: what it reads of an agent, it reads in a
documented format.
A harness's own tools
A harness may bring tools of its own, such as a shell and a file editor, and Link's tools sit beside them. Link turns off a harness's own scheduler so no job fires twice (Hermes and OpenClaw). Link adds its tools in the harness's own MCP settings and removes only its own. Each harness's page says what it keeps: Harnesses.
Namespaces
Every harness receives Link's actions by namespace. task combines run
and scheduler: run, start, read, agent, list and stop, with
send for messages to retained children. cron holds the scheduler's
schedules: create, delete and list. file combines file
operations and code lookups. agent offers send; web, browser,
desktop and memory keep their namespace names.
Task kinds
task__list lists runs and schedules together; kind selects run or
schedule. When both providers are present, task__stop requires that
selector so an ambiguous identifier never stops the wrong kind of work.
Provider policies
Each call uses its provider's existing confinement and current approval policy. The namespace does not grant more access. Changing or removing a provider takes effect on the next call, and a changed launch requires a new namespace session.
Test the tools
The tools are members of the workspace, so a test builds them beside lnk, and some run the core's lnk from the workspace's target/debug. Tests that run inside the sandbox skip without bubblewrap unless LNK_REQUIRE_SANDBOX=1 makes the missing program a failure, as CI sets it (Test Environments).