nexus-mcp

Overview Schema Source Related Servers Discussions Admin

Prompt

prompt

Destructive

Run one turn with a coding agent (Claude, Codex, or Antigravity) in a project directory and return its final answer. Delegate coding tasks and capture structured results.

Instructions

Run one turn with a coding agent and return its final answer.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cwd`	Yes	Absolute path of the project directory.
`fork`	No	Branch session_id into a new conversation instead of continuing it.
`model`	No	Model id or alias; the provider default when omitted.
`prompt`	Yes	Task for the agent.
`backend`	Yes	Agent to run.
`profile`	No	Permission profile for the agent.	read_only
`timeout`	No	Seconds before the turn is cancelled.
`session_id`	No	Continue this conversation (from a previous result).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`usage`	No
`output`	Yes
`backend`	Yes
`session_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.1.0Oct 3, 2026

changedInput schema / properties / backend / enum

Previous value: -[
-  "claude",
-  "codex"
-]New value: +[
+  "claude",
+  "codex",
+  "antigravity"
+]

Changed30 schema fields changedv2.0.1Sep 27, 2026

addedInput schema / properties / backend

Added value: +{
+  "description": "Agent to run.",
+  "enum": [
+    "claude",
+    "codex"
+  ],
+  "type": "string"
+}

removedInput schema / properties / cli

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "CLI runner name (e.g., \"codex\"). None triggers interactive selection.",
-  "enum": [
-    "claude",
-    "codex",
-    "opencode",
-    "opencode_server"
-  ]
-}

removedInput schema / properties / context

Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Optional context metadata"
-}

addedInput schema / properties / cwd

Added value: +{
+  "description": "Absolute path of the project directory.",
+  "type": "string"
+}

removedInput schema / properties / elicit

Removed value: -{
-  "anyOf": [
-    {
-      "type": "boolean"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}

removedInput schema / properties / execution_mode

Removed value: -{
-  "anyOf": [
-    {
-      "enum": [
-        "default",
-        "yolo"
-      ],
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "'default' (safe) or 'yolo'. None inherits session preference."
-}

addedInput schema / properties / fork

Added value: +{
+  "default": false,
+  "description": "Branch session_id into a new conversation instead of continuing it.",
+  "type": "boolean"
+}

removedInput schema / properties / max_retries

Removed value: -{
-  "anyOf": [
-    {
-      "type": "integer"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Max retry attempts for transient errors (None inherits session preference)."
-}

changedInput schema / properties / model / description

Previous value: -"Model name. None triggers interactive selection or uses CLI default."New value: +"Model id or alias; the provider default when omitted."

removedInput schema / properties / output_limit

Removed value: -{
-  "anyOf": [
-    {
-      "type": "integer"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Max output bytes (None inherits session preference or uses env default)."
-}

addedInput schema / properties / profile

Added value: +{
+  "default": "read_only",
+  "description": "Permission profile for the agent.",
+  "enum": [
+    "read_only",
+    "workspace_write",
+    "full_access"
+  ],
+  "type": "string"
+}

changedInput schema / properties / prompt / description

Previous value: -"Prompt text to send to the runner"New value: +"Task for the agent."

addedInput schema / properties / prompt / minLength
```
Added value: +1
```

removedInput schema / properties / retry_base_delay

Removed value: -{
-  "anyOf": [
-    {
-      "type": "number"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Base delay seconds for exponential backoff (None inherits session/config)."
-}

removedInput schema / properties / retry_max_delay

Removed value: -{
-  "anyOf": [
-    {
-      "type": "number"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Backoff ceiling in seconds (None inherits session preference or config)."
-}

addedInput schema / properties / session_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Continue this conversation (from a previous result)."
+}

removedInput schema / properties / timeout / anyOf

Removed value: -[
-  {
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]

changedInput schema / properties / timeout / default
```
Previous value: -nullNew value: +600
```

changedInput schema / properties / timeout / description

Previous value: -"Subprocess timeout seconds (None inherits session preference or uses env default)."New value: +"Seconds before the turn is cancelled."

addedInput schema / properties / timeout / minimum
```
Added value: +1
```
addedInput schema / properties / timeout / type
```
Added value: +"integer"
```

changedInput schema / required

Previous value: -[
-  "prompt"
-]New value: +[
+  "backend",
+  "prompt",
+  "cwd"
+]

addedOutput schema / description

Added value: +"Final answer of one agent turn."

addedOutput schema / properties / backend
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / output
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / result

Removed value: -{
-  "type": "string"
-}

addedOutput schema / properties / session_id
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / usage

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "backend",
+  "session_id",
+  "output"
+]

removedOutput schema / x-fastmcp-wrap-result
```
Removed value: -true
```

Changed16 schema fields changedv1.0.0May 30, 2026

addedInput schema / properties / cli / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / cli / default
```
Added value: +null
```

addedInput schema / properties / cli / description

Added value: +"CLI runner name (e.g., \"codex\"). None triggers interactive selection."

changedInput schema / properties / cli / enum

Previous value: -[
-  "claude",
-  "codex",
-  "gemini",
-  "opencode"
-]New value: +[
+  "claude",
+  "codex",
+  "opencode",
+  "opencode_server"
+]

removedInput schema / properties / cli / type
```
Removed value: -"string"
```
addedInput schema / properties / context / description
```
Added value: +"Optional context metadata"
```

addedInput schema / properties / elicit

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedInput schema / properties / execution_mode / description

Added value: +"'default' (safe) or 'yolo'. None inherits session preference."

addedInput schema / properties / max_retries / description

Added value: +"Max retry attempts for transient errors (None inherits session preference)."

addedInput schema / properties / model / description

Added value: +"Model name. None triggers interactive selection or uses CLI default."

addedInput schema / properties / output_limit / description

Added value: +"Max output bytes (None inherits session preference or uses env default)."

addedInput schema / properties / prompt / description
```
Added value: +"Prompt text to send to the runner"
```

addedInput schema / properties / retry_base_delay / description

Added value: +"Base delay seconds for exponential backoff (None inherits session/config)."

addedInput schema / properties / retry_max_delay / description

Added value: +"Backoff ceiling in seconds (None inherits session preference or config)."

addedInput schema / properties / timeout / description

Added value: +"Subprocess timeout seconds (None inherits session preference or uses env default)."

changedInput schema / required

Previous value: -[
-  "cli",
-  "prompt"
-]New value: +[
+  "prompt"
+]

First observedv0.8.1Mar 22, 2026

TDQS

B3.1/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=true. The description adds only that it runs 'one turn' and returns a 'final answer,' which is minimal behavioral context. It does not disclose side effects, permission implications, or session handling details beyond what the schema and annotations provide.

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

Conciseness5/5

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

The description is a single, efficient sentence that is front-loaded and contains no redundant or filler language. Every word contributes to the core purpose.

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

Completeness3/5

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

An output schema exists, so return values need not be explained. Annotations cover the safety profile. However, for a tool with 8 parameters and a destructive, open-world operation, the description lacks usage context and behavioral details that would help an agent invoke it correctly. It is minimally viable given the structured data.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema fully documents all 8 parameters. The description adds no additional semantic meaning for any parameter. Baseline 3 is appropriate when the schema carries the full descriptive burden.

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

Purpose4/5

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

The description provides a specific verb and resource: 'Run one turn with a coding agent and return its final answer.' It clearly states what the tool does. However, there are no sibling tools to differentiate from, and the description does not elaborate on scope or distinctions.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives, nor any preconditions or exclusions. The single sentence simply states the action without context for selection.

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

Deploy Server

Other Tools

promptB