Tools
The agent acts through tools. Each tool has a default decision: allow runs it, ask waits
for a person. A Rule changes the default, and Permissions explains how.
This page lists the tool names, so you can write a Rule without looking them up first.
wisp permissions get shows the tools you are likely to write a Rule for, with the
decision that applies now. It leaves out the agent's own mechanics: memory_*,
preference_*, diagnostics_read, skill_*, spawn_agent, and a connector's
list_resources, read_resource, list_prompts and get_prompt. A Rule for any of them
still works.
Files
The file tools work in the Session's folder: its Project, or, for a Session without a
Project, a folder of its own under ~/Wisp.
| Tool | What it does | Default |
|---|---|---|
fs_read | reads a text file; a PDF, .docx, .xlsx or .pptx is turned into text | allow |
fs_read_media | shows the agent an image: PNG, JPEG, GIF or WebP | allow |
fs_list | lists files and folders | allow |
fs_glob | finds files by name pattern | allow |
fs_grep | searches file contents | allow |
fs_write | creates or overwrites a file | ask |
fs_edit | replaces exact text in a file | ask |
deliver_file | sends you a file from the folder, attached after the answer; see Voice and files | allow |
generate_image | makes a picture from a description and saves it in the folder as a JPEG; see Pictures the agent makes | allow |
How far they reach follows the sandbox switch:
- Sandbox on: a path outside the folder is refused.
- Sandbox off, the default: a path outside the folder is allowed, but every such call
asks, on a card that names where it lands, whatever the Rules say. Under
wisp runit is refused.
generate_image is the exception: its path must stay inside the folder whatever the switch,
and a path outside it is refused, never asked.
Either way some paths are always refused: Wisp's data directory (~/.wisp), the Project's
own .wisp/ (except .wisp/mcp.json, which can be read), .env files (.env.example,
.env.sample and .env.template excepted), /etc, and the secrets in your home folder,
such as ~/.ssh, ~/.aws, ~/.gnupg, ~/.npmrc, ~/.gitconfig, shell history and the
macOS Keychain.
Shell
| Tool | What it does | Default |
|---|---|---|
bash_run | runs a shell command, in a sandbox | ask |
Read bash_run before you allow it: the
sandbox is off by default, and once on it keeps a command inside its folder,
but its network is on. By default a command stops after 30 seconds (bashTimeout) and
its output is cut at 100,000 characters (bashMaxOutput); the agent can set either for one
command.
Schedules
The agent can make a scheduled job from a chat: "every weekday at nine, summarise my inbox".
| Tool | What it does | Default |
|---|---|---|
schedule_create | creates a job | ask |
schedule_update | changes a job | ask |
schedule_delete | deletes a job | ask |
schedule_list | lists the jobs | allow |
schedule_pause | pauses a job | allow |
These tools differ from the rest in two ways:
- They are offered only to a Run a person can answer. A Run in the
policymode, which is the default forwisp runand/v1, and every Run a job fires, does not see them at all, whatever the Rules say. - Creating, changing or deleting a job asks every time. A Rule or a Project bypass that
says
allowis still anaskfor these three. Adenyis still adeny.
A Run from a chat sees only that chat's jobs.
Skills
| Tool | What it does | Default |
|---|---|---|
skill_invoke | runs a Skill by name | allow |
skill_fs_read | reads a file of a Skill | allow |
skill_fs_list | lists Skills, or the files of one | allow |
skill_fs_write | creates or changes a file of a Skill | allow |
skill_fs_delete | deletes a file of a Skill, or the whole Skill | ask |
skill_fs_write defaults to allow. The agent can create or change a Skill in
~/.wisp/skills/<name>/, which every Project sees, or in the Project's
.settings/skills/<name>/, and no one is asked. A Skill it writes there is offered to later
Runs too. Built-in Skills cannot be changed. To be asked first:
wisp permissions set skill_fs_write ask
Memory and other agent tools
| Tool | What it does | Default |
|---|---|---|
memory_store | saves a memory, tied to this Session or kept for good | allow |
memory_recall | finds memories by text, tag or type | allow |
memory_update | changes a memory | allow |
memory_delete | deletes a memory | allow |
memory_get_all | reads every memory, with no filter | ask |
preference_get | reads a stored preference of the user | allow |
preference_set | stores a preference of the user | allow |
spawn_agent | starts a subagent for part of the task | allow |
diagnostics_read | reads the Runtime's recent errors and warnings | allow |
recording_list | lists meeting recordings | allow |
recording_read | reads a recording's transcript | allow |
recording_search | searches recordings for a topic | allow |
recording_delete | deletes a recording and its transcript | ask |
The agent also remembers on its own. After each turn in which it stored nothing itself, the
Runtime asks the model what in the turn is worth keeping and saves that. Before each turn
it adds the memories and preferences that look relevant, from every Session and Project, and
points the agent at recordings that do. A memory the agent marks project is not limited
to the Project: it is offered everywhere, and it is deleted with the Session that stored it.
A global one stays until it is deleted.
A subagent can use every tool the agent has, writing files included, unless the agent
narrows it to the read tools and bash_run. Its tool calls go through the same Rules as the
agent's own. It has no step or time limit by default; subagentTimeoutMs in the
configuration sets a time limit.
Connector tools
Each connector adds its own tools, named mcp__<connector>__<tool>. Every
one of them defaults to ask, whatever the server says about it.
A connector whose server offers resources or prompts also gets four tools that default to
allow:
mcp__<connector>__list_resourcesmcp__<connector>__read_resourcemcp__<connector>__list_promptsmcp__<connector>__get_prompt
wisp permissions get --connector <name> lists one connector's tools.
How the agent reaches them
Connector tools are not in the agent's own tool list, so that dozens of them do not crowd its context. The agent gets a short catalog of them and two tools to use it:
mcp_searchfinds connector tools by what they do and returns each one's arguments.mcp_callruns one connector tool by its name.
So in Wisp Desktop and in the audit log you may see the agent search before it acts. The first call of a tool whose arguments the agent has not read yet is not run: it gets the tool's arguments back and calls again. That refused call is expected and changes nothing.
Rules, approval cards and the audit log still use the connector tool's own name,
mcp__<connector>__<tool>, never mcp_call. The web tools of wisp_proxy are the
exception: they are in the agent's own list and called directly.
A subagent or a fork Skill that is given a list of tools reaches connectors only when
the list names mcp_call or mcp_search; then it can use every connector tool its Project
enables. With no list, it gets them as the agent does.
Web search and fetch
The agent reaches the web through the Wisp proxy's own connector, wisp_proxy. It needs no
wisp connectors add and no enable, and wisp connectors list does not show it. Its tools:
| Tool | What it does | Default |
|---|---|---|
mcp__wisp_proxy__brave_search | searches the web | ask |
mcp__wisp_proxy__fetch_url | fetches a page as text | ask |
mcp__wisp_proxy__curl | sends any HTTP request, POST and DELETE among them | ask |
Like every connector tool they ask, so under wisp run the agent cannot search the web
until a Rule allows it. Allow the two that read:
wisp permissions set mcp__wisp_proxy__brave_search allow
wisp permissions set mcp__wisp_proxy__fetch_url allow
wisp permissions allow-connector wisp_proxy allows mcp__wisp_proxy__curl as well, and
that lets the agent send data to any address. Allow the tools one by one unless you mean it.
mcp__wisp_proxy__brave_search is there only when the proxy has search set up.
wisp permissions get --connector wisp_proxy shows what your proxy offers.