Skip to main content

Overview

ToolCategoryDefaultGateDescription
task_createTaskYesCreate a new task
task_getTaskYesGet a task by ID
task_listTaskYesList tasks with optional filters
task_updateTaskYesUpdate an existing task
shellShellNoExecute a shell command
shell_jobsShellNoList background shell jobs
shell_job_statusShellNoCheck background job status
shell_job_cancelShellNoCancel a background job
memory_searchMemoryN/Amemory-store-sessionSearch semantic memory
waitUtilityYesPause execution
datetimeUtilityYesGet current date/time
apply_patchUtilityYesApply structured file patches inside the project root
view_imageUtilityYesvisionRead an image file and return base64 content
sendCommsYescommsSend message/request/response to a peer
peersCommsYescommsList discoverable peers (trusted + inproc)

Enabling and disabling tools

AgentFactory controls which tool categories are available via builder methods:
FlagBuilder MethodDefaultControls
enable_builtins.builtins(bool)falseTask tools, utility tools (wait, datetime, apply_patch)
enable_shell.shell(bool)falseAll shell tools (shell, shell_jobs, shell_job_status, shell_job_cancel)
enable_memory.memory(bool)falsememory_search (requires memory-store-session feature)
enable_comms.comms(bool)falseAll comms tools (requires comms feature)
enable_mob.mob(bool)falseMob orchestration tools (mob_*, meerkat_*)
AgentFactory is the only place tool categories are composed. AgentBuilder (in meerkat-core) has no dependency on meerkat-tools and does not auto-register any tools — it takes a pre-built dispatcher. See AgentBuilder vs AgentFactory.Source: meerkat/src/factory.rsAgentFactory struct and builder methods.
Each AgentBuildConfig can override factory-level flags for a single agent build:
Override FieldTypeEffect
override_builtinsOption<bool>Takes precedence over enable_builtins when Some
override_shellOption<bool>Takes precedence over enable_shell when Some
override_memoryOption<bool>Takes precedence over enable_memory when Some
override_mobOption<bool>Takes precedence over enable_mob when Some
All default to None (use factory-level setting).Source: meerkat/src/factory.rsAgentBuildConfig struct.
Individual tools can be enabled or disabled via ToolPolicyLayer in BuiltinToolConfig. When shell is enabled, a ToolPolicyLayer is applied that activates the four shell tools (which have default_enabled: false).
Capabilities are registered via the inventory crate in meerkat-tools/src/lib.rs:
  • Builtins (CapabilityId::Builtins): task_list, task_create, task_get, task_update, wait, datetime, apply_patch, view_image. Controlled by config.tools.builtins_enabled.
  • Shell (CapabilityId::Shell): shell, shell_jobs, shell_job_status, shell_job_cancel. Controlled by config.tools.shell_enabled.

Runtime tool scoping

Beyond static factory flags and per-build overrides, tool visibility can be changed at runtime during a live session. See Tool scoping for the conceptual overview.
ToolScope (in meerkat-core) manages runtime tool visibility. It holds the base tool set from the dispatcher, an active external filter, and an optional per-turn overlay.Staging: External callers stage filter updates via ToolScopeHandle::stage_external_filter(filter). The staged filter is NOT applied immediately — the current turn is unaffected.Boundary apply: At the start of each CallingLlm loop iteration, tool_scope.apply_staged(dispatcher_tools) atomically promotes the staged filter to active, prunes stale tool names, and returns the visible tool set. A ToolConfigChanged event is emitted and a [SYSTEM NOTICE] is injected into the conversation.Filter types:
  • ToolFilter::All — no restriction (default)
  • ToolFilter::Allow(set) — only listed tools are visible
  • ToolFilter::Deny(set) — listed tools are hidden
Composition: Most-restrictive wins. Multiple allow-lists intersect, multiple deny-lists union, deny beats allow.Persistence: The active external filter is stored in session metadata under tool_scope_external_filter and restored on session resume.Source: meerkat-core/src/tool_scope.rs
MCP servers can be added or removed from a running session. Operations are staged on the McpRouter and applied at the next turn boundary.
SurfaceMethodStatus
JSON-RPCmcp/add, mcp/remove, mcp/reloadFully wired (staged)
RESTPOST /sessions/{id}/mcp/add|remove|reloadRoutes registered (placeholder)
CLIrkat mcp add/remove --session <id> --live-server-url <url>Delegates to REST
Servers being removed transition through Active → Removing (draining) → Removed to allow in-flight tool calls to complete before finalization.Source: meerkat-mcp/src/router.rs, meerkat-rpc/src/handlers/mcp.rs
Mob flow steps can restrict tools for a single turn via TurnToolOverlay:
TurnToolOverlay {
    allowed_tools: Option<Vec<String>>,  // allow-list for this turn
    blocked_tools: Option<Vec<String>>,  // deny-list for this turn
}
Set on StartTurnRequest.flow_tool_overlay by the flow engine. Ephemeral — cleared after the turn completes. Composes with the external filter using most-restrictive semantics.Source: meerkat-core/src/service/mod.rs, meerkat-mob/src/runtime/flow.rs

Task tools

Task tools provide structured work tracking. They are enabled by default when builtins are on. Tasks are persisted via TaskStore (either FileTaskStore on disk or MemoryTaskStore in-memory).
A Task object returned by task tools has these fields:
FieldTypeDescription
idStringUnique task identifier
subjectStringShort subject/title
descriptionStringDetailed description
statusString"pending", "in_progress", or "completed"
priorityString"low", "medium", or "high"
labelsString[]Labels/tags for categorization
blocksString[]IDs of tasks that this task blocks
blocked_byString[]IDs of tasks that block this task
created_atStringISO 8601 creation timestamp
updated_atStringISO 8601 last-updated timestamp
created_by_sessionString?Session ID that created this task
updated_by_sessionString?Session ID that last updated this task
ownerString?Owner/assignee (agent name or user identifier)
metadataObjectArbitrary key-value metadata
Source: meerkat-tools/src/builtin/types.rsTask struct.
Create a new task in the project task list.Default enabled: Yes
subject
String
required
Short subject/title of the task.
description
String
required
Detailed description of what needs to be done.
priority
String
default:"medium"
"low", "medium", or "high".
labels
String[]
default:"[]"
Labels/tags for categorization.
blocks
String[]
default:"[]"
Task IDs that this task blocks.
blocked_by
String[]
default:"[]"
Task IDs that block this task.
owner
String
default:"null"
Owner/assignee.
metadata
Object
default:"{}"
Arbitrary key-value metadata.
Returns: The created Task object (see task data model above).Source: meerkat-tools/src/builtin/tasks/task_create.rs
Get a task by its ID.Default enabled: Yes
id
String
required
The task ID to retrieve.
Returns: The Task object matching the given ID.Error: ExecutionFailed if the task ID is not found.Source: meerkat-tools/src/builtin/tasks/task_get.rs
List tasks in the project, optionally filtered by status or labels.Default enabled: Yes
status
String
default:"null (all)"
Filter by status: "pending", "in_progress", or "completed".
labels
String[]
default:"null (all)"
Filter by labels (tasks matching any label).
Returns: Array of Task objects matching the filters.Source: meerkat-tools/src/builtin/tasks/task_list.rs
Update an existing task. Only provided fields are modified; omitted fields remain unchanged.Default enabled: Yes
id
String
required
The task ID to update.
subject
String
default:"unchanged"
New subject/title.
description
String
default:"unchanged"
New description.
status
String
default:"unchanged"
New status: "pending", "in_progress", or "completed".
priority
String
default:"unchanged"
New priority: "low", "medium", or "high".
labels
String[]
default:"unchanged"
Replace all labels.
owner
String
default:"unchanged"
New owner/assignee.
metadata
Object
default:"unchanged"
Merge metadata (set key to null to remove).
add_blocks
String[]
default:"[]"
Task IDs to add to the blocks list.
remove_blocks
String[]
default:"[]"
Task IDs to remove from the blocks list.
add_blocked_by
String[]
default:"[]"
Task IDs to add to the blocked_by list.
remove_blocked_by
String[]
default:"[]"
Task IDs to remove from the blocked_by list.
Returns: The updated Task object.Error: ExecutionFailed if the task ID is not found.Source: meerkat-tools/src/builtin/tasks/task_update.rs

Shell tools

Shell tools execute commands and manage background jobs. They are all default_enabled: false and require the factory-level enable_shell flag (or a ToolPolicyLayer override) to be active.
Shell behavior is controlled by ShellConfig:
Config FieldTypeDefaultDescription
enabledboolfalseMaster switch for shell tools
default_timeout_secsu6430Default command timeout
restrict_to_projectbooltrueRestrict working dirs to project root
shellString"nu"Shell binary name (Nushell by default; falls back to bash/zsh/sh)
shell_pathPathBuf?NoneExplicit shell binary path
project_rootPathBufCWDProject root for path restriction
max_completed_jobsusize100Maximum completed jobs retained
completed_job_ttl_secsu64300TTL for completed job records (seconds)
max_concurrent_processesusize10Maximum concurrent background processes
security_modeSecurityModeUnrestrictedCommand security policy
security_patternsVec<String>[]Glob patterns for allow/deny lists
Source: meerkat-tools/src/builtin/shell/config.rs
The SecurityEngine validates commands before execution using POSIX-compliant word splitting (shlex) and glob pattern matching (globset).
ModeBehavior
UnrestrictedAll commands allowed (default)
AllowListOnly commands matching security_patterns globs are allowed
DenyListCommands matching security_patterns globs are rejected
Patterns are matched against the canonicalized command invocation. The engine parses the full command string into individual words, then validates the executable (first word) and the full command string against the pattern set.Source: meerkat-tools/src/builtin/shell/security.rs
Execute a shell command. Uses POSIX-style parsing for policy checks; runs via Nushell or fallback shell.Default enabled: No (requires shell to be enabled)
command
String
required
The command to execute (POSIX-style parsing for policy checks).
working_dir
String
default:"Project root"
Working directory (relative to project root).
timeout_secs
u64
default:"Config default (30)"
Timeout in seconds.
background
bool
default:"false"
If true, run in background and return job ID immediately.
{
  "exit_code": 0,
  "stdout": "...",
  "stderr": "...",
  "timed_out": false,
  "duration_secs": 1.23
}
Output is truncated to the last 100,000 characters if it exceeds that limit. Fields stdout_lossy and stderr_lossy indicate whether output was lossy-decoded from non-UTF-8 bytes.
Source: meerkat-tools/src/builtin/shell/tool.rs
List all background shell jobs.Default enabled: No (requires shell to be enabled)Parameters: None (empty object).
[
  {
    "id": "job_<uuid-v7>",
    "command": "echo hello",
    "status": "running",
    "started_at_unix": 1700000000
  }
]
The status field is one of: "running", "completed", "failed", "timed_out", "cancelled".Source: meerkat-tools/src/builtin/shell/jobs_list_tool.rs
Check status of a background shell job. Returns full job details including output when complete.Default enabled: No (requires shell to be enabled)
job_id
String
required
The job ID to check.
{
  "id": "job_<uuid-v7>",
  "command": "echo test",
  "working_dir": "/path/to/project",
  "timeout_secs": 30,
  "started_at_unix": 1700000000,
  "status": "completed"
}
Error: ExecutionFailed if the job ID is not found.Source: meerkat-tools/src/builtin/shell/job_status_tool.rs
Cancel a running background shell job.Default enabled: No (requires shell to be enabled)
job_id
String
required
The job ID to cancel.
{
  "job_id": "job_<uuid-v7>",
  "status": "cancelled"
}
Error: ExecutionFailed if the job ID is not found.Source: meerkat-tools/src/builtin/shell/job_cancel_tool.rs
JobId format: "job_" followed by a UUID v7 string.JobStatus variants: Running, Completed, Failed, TimedOut, Cancelled (serialized as lowercase snake_case strings).Source: meerkat-tools/src/builtin/shell/types.rs

Memory tool

The memory search tool lives in the meerkat-memory crate and is composed into the tool dispatcher as a separate MemorySearchDispatcher (implementing AgentToolDispatcher). It is NOT part of CompositeDispatcher — it is wired via ToolGateway when the memory-store-session feature is enabled and enable_memory is true.

Utility tools

Utility tools are general-purpose helpers enabled by default when builtins are on.
Pause execution for the specified number of seconds. Supports fractional seconds. Useful for polling loops or rate limiting.Default enabled: Yes
seconds
f64
required
Duration to wait in seconds (clamped to 0.0 to 60.0).
Maximum wait time is 60 seconds (1 minute). Values are clamped to the range 0.0 to 60.0.
{
  "waited_seconds": 5.0,
  "status": "complete"
}
Source: meerkat-tools/src/builtin/utility/wait.rs
Get the current date and time. Returns ISO 8601 formatted datetime and Unix timestamp.Default enabled: YesParameters: None (empty object).
{
  "iso8601": "2025-01-15T14:30:00+01:00",
  "date": "2025-01-15",
  "time": "14:30:00",
  "timezone": "+01:00",
  "unix_timestamp": 1736949000,
  "year": 2025,
  "month": 1,
  "day": 15,
  "weekday": "Wednesday"
}
Source: meerkat-tools/src/builtin/utility/datetime.rs
Read an image file from the project directory and return its contents as a base64-encoded ContentBlock::Image. This enables vision-capable models to analyze images from disk during tool use.Default enabled: Yes (when builtins are on and model supports vision)
path
String
required
Path to the image file, relative to the project root.
Supported formats: PNG, JPEG, GIF, WebP, SVG.Size limit: 5 MB. Files exceeding this limit return an error.Capability gating: view_image is automatically hidden via ToolScope when the active model does not support vision (i.e., ModelProfile.vision == false). It is also hidden when the model does not support image content in tool results (ModelProfile.image_tool_results == false). This means the tool never appears in the tool list sent to models that cannot process image content.Returns: A ToolOutput::Blocks containing a single ContentBlock::Image with the base64-encoded image data and detected media type. The source_path field is set on the domain type but stripped from the wire representation (WireContentBlock).Source: meerkat-tools/src/builtin/utility/view_image.rs

Comms tools

Comms tools enable inter-agent communication. They require the comms Cargo feature (dep:meerkat-comms) and the factory-level enable_comms flag. Unlike other tool categories, comms tools are provided as a separate CommsToolSurface dispatcher (implementing AgentToolDispatcher) and composed via ToolGateway, NOT bundled into CompositeDispatcher. Comms tools are only shown to the agent when at least one peer is discoverable (controlled by CommsToolSurface::peer_availability()). The check passes when TrustedPeers has entries. Tool definitions (name, description, input schema) are dynamically loaded from meerkat_comms::tools_list().
Send a message, request, or response to a trusted peer. The kind parameter determines the message type.Default enabled: Yes (when comms is active)
to
String
required
Peer name to send to.
kind
String
required
Message kind: "peer_message", "peer_request", or "peer_response".
body
String
Message content (required when kind="peer_message").
intent
String
Request intent/action identifier (required when kind="peer_request").
params
any
default:"null"
Request parameters (for kind="peer_request").
in_reply_to
String (UUID)
ID of the request being responded to (required when kind="peer_response").
status
String
Response status: "accepted", "completed", or "failed" (required when kind="peer_response").
result
any
default:"null"
Response result data (for kind="peer_response").
{
  "status": "sent",
  "kind": "peer_message"
}
Source: meerkat-comms/src/mcp/tools.rsSendInput
List all discoverable peers and their connection status.Returns configured trusted peers (TrustedPeers), excluding the current agent (“self”) by public key.Default enabled: Yes (when comms is active)Parameters: None (empty object).
{
  "peers": [
    {
      "name": "agent-beta",
      "peer_id": "<derived-peer-id>",
      "address": "tcp://127.0.0.1:4200"
    }
  ]
}
Source: meerkat-comms/src/mcp/tools.rsPeersInput

Cargo feature gates

Tool availability depends on compile-time features in the meerkat-tools crate:
FeatureDefaultDependenciesTools unlocked
commsYesdep:meerkat-commssend, peers
mcpYesdep:meerkat-mcpExternal MCP tool routing (not builtin tools)
The memory_search tool is gated by the memory-store-session feature on the meerkat facade crate (not meerkat-tools), since MemorySearchDispatcher lives in meerkat-memory. Source: meerkat-tools/Cargo.toml