Skip to main content
Glama

Boruna Manage Tool

boruna_manage
Destructive

Execute, validate, and audit Boruna scripts with deterministic capability-safe runtime. Manage script execution, policies, and skill lifecycle.

Instructions

Boruna deterministic capability-safe .ax script runtime (v1.x LTS) — execute, validate, and audit Boruna scripts. Side effects depend entirely on the script's declared capabilities. Requires an active mcp_stdio Tool record pointing to a working Boruna binary; otherwise every action returns dependency_unavailable.

Actions:

  • run (write — side effects per script capabilities) — inline .ax source OR skill_id of a saved boruna_script skill; optional: timeout_ms, mem_limit_mb.

  • validate (read) — .ax source. Syntax + semantic check, no execution.

  • policy_validate (read; v0.4.0+) — policy JSON. Strict schema validation.

  • evidence (read) — run_id. Capability/effect evidence record for an executed run.

  • capability_list (read) — registered capabilities and capability_set_hash.

  • skill_manage (write) — sub-actions list/get/create/update/delete on boruna_script-typed skills.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: run, validate, policy_validate, evidence, capability_list, skill_manage
deadline_msNoOptional: max wall-clock time (ms) the tool may spend. If exceeded during the call, returns a DEADLINE_EXCEEDED error. Minimum 100 ms. Leave unset for no deadline.
modeYesExecution mode: inline (run script directly) or skill (run a saved boruna_script skill)
scriptNo(inline mode) The .ax script source code to execute
policyNo(inline mode) Legacy capability policy shorthand: "allow-all" or "deny-all" (default: deny-all). For Boruna v0.2.0+ fine-grained gating, use policy_structured instead.
policy_structuredNo(inline mode, Boruna v0.2.0+) Structured Capability Policy object with required default_allow (bool), optional rules (per-capability {allow, budget}), and optional net_policy (allowed_domains, allowed_methods, max_response_bytes, timeout_ms, allow_redirects). Capability keys: net.fetch, fs.read, fs.write, db.query, ui.render, time.now, random, llm.call, actor.spawn, actor.send. When set, takes precedence over the legacy policy parameter. See https://github.com/escapeboy/boruna/blob/v0.2.0/docs/reference/policy-schema.md.
boruna_tool_idNo(inline mode) UUID of the mcp_stdio Tool pointing to the Boruna binary. If omitted, auto-detects.
inputNoOptional input data passed to the script as JSON
limitsNo(inline mode, v1.0+) Optional resource limits: max_wall_ms (int) and/or max_output_bytes (int)
skill_idNo(skill mode) UUID of the boruna_script Skill to execute
policy_jsonYesJSON-encoded Boruna policy object to validate. Must have a top-level default_allow boolean. Example: {"default_allow":false,"rules":{"net.fetch":{"allow":true}}}
execution_idYesUUID of the SkillExecution record from a boruna_script skill run
nameNo(create) Skill name
descriptionNo(create) Skill description
limitNo(list | executions) Max results (default 20)
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that side effects depend on script capabilities, notes the 'dependency_unavailable' error, and categorizes actions as 'write' (run) or 'read' (others). This aligns with the destructiveHint: true annotation and adds context beyond it, though detailed effects per script are left to the script's capabilities.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is lengthy but well-structured with bullet points for each action and clear parameter groupings. It is not overly verbose given the complexity of the tool, and every sentence adds useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 15 parameters, multiple actions, no output schema, and complex dependencies, the description covers actions, error conditions, prerequisite setup, and parameter usage. It references external documentation for further details. Minor gaps: no description of return values for each action.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage, but the description adds meaning by grouping parameters per action (e.g., inline vs skill mode), explaining the relationship between 'policy' and 'policy_structured', and specifying which parameters are relevant for each action. This goes beyond the schema's property descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool executes, validates, and audits Boruna scripts, and lists specific actions (run, validate, etc.) with their purposes. It distinguishes from sibling tools (e.g., admin_manage, agent_manage) by focusing on Boruna-specific functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use each sub-action (e.g., 'run for execution, validate for syntax check') and mentions a prerequisite (mcp_stdio Tool record). However, it does not explicitly compare this tool to alternatives or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/escapeboy/agent-fleet-o'

If you have feedback or need assistance with the MCP directory API, please join our Discord server