Keel — Hyperliquid trading strategies

Fork Strategy

keel_strategy_fork

Copy a strategy into your organization as an independent strategy with its own history; the original stays unchanged. Accepts a strategy ID or share-link ID.

Instructions

Copy a strategy into the caller's org as a separate strategy with its own history; the original's source and versions are unchanged (saving a new version of a strategy is keel_strategy_compose). The copy starts with one version and no backtests; the original keeps its versions and their backtests. source is a strategy id (str_*) or the id in a usekeel.io/share/<id> URL showing its source, any organisation's; forking one adds to its public fork count. Sharing is keel_share_create.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source": "<source>"
    },
    "name": "keel_strategy_fork"
  }
}

Input Schema

Name	Required	Description
`name`	No	Optional new name for the fork. It names the strategy — its market, thesis or method (e.g. `HYPE MACD trend`) — and is shown wherever the strategy is listed; the user's own name or account belongs to the account, not to a strategy name.
`source`	Yes	Strategy id (`str_*`) or share-link id (the token in a `usekeel.io/share/<id>` URL).
`present`	No	How this result displays in the chat — presentation only, no effect on what the tool does. `view`: the full card, for showing the result in full or enlarged. `receipt`: a compact one-line summary row, for the one-line or short version. Omitted: `view`.
`description`	No	The fork's thesis in the user's own words — one or two sentences on what this copy is for and what it changes (not a transcript of the conversation). Shown on the strategy page in the Keel app, where the user can edit it.
`target_workspace_id`	No	Workspace to place the fork in (default: org default); it must belong to the caller's org, and the result's `workspace_id` names where the fork landed.

Output Schema

Name	Required	Description
`code`	No
`cost`	No
`info`	No
`mode`	No
`name`	No
`next`	No
`slug`	No
`view`	No	One strategy: its structure graph, change marks, evidence and the rendered markdown.
`added`	No
`error`	No
`quota`	No
`ref_a`	No
`ref_b`	No
`stale`	No
`detail`	No
`parent`	No
`reason`	No
`resume`	No
`run_id`	No
`source`	No
`changed`	No
`dry_run`	No
`example`	No
`message`	No
`removed`	No
`version`	No
`category`	No
`compiled`	No
`docs_url`	No
`headline`	No
`hero_url`	No
`metadata`	No
`universe`	No
`url_line`	No
`variants`	No
`versions`	No
`exit_code`	No
`fork_note`	No
`reference`	No	BTC hold, price only, over the run's span (run 1's on a comparison).
`reordered`	No
`retryable`	No
`risk_band`	No
`share_url`	No
`sync_note`	No
`unchanged`	No
`action_url`	No
`data_as_of`	No
`limit_view`	No
`validation`	No
`variant_id`	No
`recent_runs`	No	The strategy's newest backtest runs, newest first (up to 5): run_id, status, version, the version's commit message, window, completed_at and the headline metrics.
`source_slug`	No
`strategy_id`	No
`declarations`	No
`head_summary`	No
`new_sequence`	No
`quota_notice`	No
`resource_uri`	No
`source_error`	No
`summary_text`	No
`compile_error`	No
`entry_version`	No
`error_message`	No
`library_facts`	No
`limit_details`	No
`new_commit_id`	No
`blocked_action`	No
`required_actor`	No
`talking_points`	No
`versions_error`	No
`workspace_sync`	No
`backtest_window`	No
`missing_evidence`	No
`ownership_status`	No
`unavailable_code`	No
`description_error`	No
`restored_from_ref`	No
`what_was_expected`	No
`default_variant_id`	No
`is_default_variant`	No
`unavailable_reason`	No
`projection_available`	No
`suggested_next_action`	No
`ownership_resource_uri`	No
`restored_from_sequence`	No
`live_readiness_blockers`	No
`next_recommended_action`	No
`component_version_changes`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed99 schema fields changedv0.9.0Oct 17, 2026

addedInput schema / properties / description

Added value: +{
+  "description": "The fork's thesis in the user's own words — one or two sentences on what this copy is for and what it changes (not a transcript of the conversation). Shown on the strategy page in the Keel app, where the user can edit it.",
+  "maxLength": 2000,
+  "type": "string"
+}

changedInput schema / properties / name / description

Previous value: -"Optional new name for the fork."New value: +"Optional new name for the fork. It names the strategy — its market, thesis or method (e.g. `HYPE MACD trend`) — and is shown wherever the strategy is listed; the user's own name or account belongs to the account, not to a strategy name."

addedInput schema / properties / name / maxLength
```
Added value: +255
```
addedInput schema / properties / name / minLength
```
Added value: +1
```

addedInput schema / properties / present

Added value: +{
+  "description": "How this result displays in the chat — presentation only, no effect on what the tool does. `view`: the full card, for showing the result in full or enlarged. `receipt`: a compact one-line summary row, for the one-line or short version. Omitted: `view`.",
+  "enum": [
+    "receipt",
+    "view"
+  ],
+  "type": "string"
+}

changedInput schema / properties / source / description

Previous value: -"Strategy id (`str_*`) or share-link id."New value: +"Strategy id (`str_*`) or share-link id (the token in a `usekeel.io/share/<id>` URL)."

changedInput schema / properties / target_workspace_id / description

Previous value: -"Workspace to place the fork in (default: org default)."New value: +"Workspace to place the fork in (default: org default); it must belong to the caller's org, and the result's `workspace_id` names where the fork landed."

addedOutput schema / description

Added value: +"A strategy result: `view` renders it; an error carries `code` and `message` instead."

addedOutput schema / properties / action_url
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / added
```
Added value: +{
+  "type": "array"
+}
```
addedOutput schema / properties / backtest_window
```
Added value: +{}
```
addedOutput schema / properties / blocked_action
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / category

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

addedOutput schema / properties / changed
```
Added value: +{
+  "type": "array"
+}
```
addedOutput schema / properties / code
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / compile_error

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

addedOutput schema / properties / compiled
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / component_version_changes
```
Added value: +{}
```
addedOutput schema / properties / cost
```
Added value: +{
+  "type": "object"
+}
```

addedOutput schema / properties / data_as_of

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

addedOutput schema / properties / declarations
```
Added value: +{
+  "type": "object"
+}
```

addedOutput schema / properties / default_variant_id

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

addedOutput schema / properties / description_error
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / detail
```
Added value: +{
+  "type": "object"
+}
```

addedOutput schema / properties / docs_url

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

addedOutput schema / properties / dry_run
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / entry_version
```
Added value: +{}
```
addedOutput schema / properties / error
```
Added value: +{}
```

addedOutput schema / properties / error_message

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

addedOutput schema / properties / example
```
Added value: +{}
```
addedOutput schema / properties / exit_code
```
Added value: +{
+  "type": "integer"
+}
```
addedOutput schema / properties / fork_note
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / head_summary
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / headline
```
Added value: +{}
```
addedOutput schema / properties / hero_url
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / info
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / is_default_variant

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

addedOutput schema / properties / library_facts
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / limit_details
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / limit_view
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / live_readiness_blockers
```
Added value: +{
+  "type": "array"
+}
```
addedOutput schema / properties / message
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / metadata
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / missing_evidence
```
Added value: +{
+  "type": "array"
+}
```
addedOutput schema / properties / mode
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / name

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

addedOutput schema / properties / new_commit_id

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

addedOutput schema / properties / new_sequence

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

addedOutput schema / properties / next

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

addedOutput schema / properties / next_recommended_action
```
Added value: +{}
```

addedOutput schema / properties / ownership_resource_uri

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

addedOutput schema / properties / ownership_status

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

addedOutput schema / properties / parent
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / projection_available
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / quota
```
Added value: +{
+  "type": "array"
+}
```
addedOutput schema / properties / quota_notice
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / reason
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / recent_runs

Added value: +{
+  "description": "The strategy's newest backtest runs, newest first (up to 5): run_id, status, version, the version's commit message, window, completed_at and the headline metrics.",
+  "items": {
+    "properties": {
+      "completed_at": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "message": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "metrics": {
+        "type": "object"
+      },
+      "run_id": {
+        "type": "string"
+      },
+      "status": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "version": {
+        "type": [
+          "integer",
+          "string",
+          "null"
+        ]
+      },
+      "window": {
+        "type": "object"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

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

addedOutput schema / properties / reference

Added value: +{
+  "description": "BTC hold, price only, over the run's span (run 1's on a comparison).",
+  "properties": {
+    "basis": {
+      "type": "string"
+    },
+    "dd_pct": {
+      "maximum": 0,
+      "type": "number"
+    },
+    "label": {
+      "type": "string"
+    },
+    "ret_pct": {
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / removed
```
Added value: +{
+  "type": "array"
+}
```
addedOutput schema / properties / reordered
```
Added value: +{}
```
addedOutput schema / properties / required_actor
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / resource_uri
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / restored_from_ref
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / restored_from_sequence

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

removedOutput schema / properties / result

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

addedOutput schema / properties / resume
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / retryable
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / risk_band
```
Added value: +{}
```
addedOutput schema / properties / run_id
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / share_url

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

addedOutput schema / properties / slug

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

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

addedOutput schema / properties / source_slug

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

addedOutput schema / properties / stale

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

addedOutput schema / properties / strategy_id

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

addedOutput schema / properties / suggested_next_action
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / summary_text
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / sync_note
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / talking_points
```
Added value: +{
+  "type": "array"
+}
```
addedOutput schema / properties / unavailable_code
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / unavailable_reason
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / unchanged
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / universe
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / url_line
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / validation
```
Added value: +{
+  "type": "object"
+}
```

addedOutput schema / properties / variant_id

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

addedOutput schema / properties / variants
```
Added value: +{}
```

addedOutput schema / properties / version

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

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

addedOutput schema / properties / view

Added value: +{
+  "description": "One strategy: its structure graph, change marks, evidence and the rendered markdown.",
+  "properties": {
+    "at": {
+      "type": "string"
+    },
+    "categories": {},
+    "change": {},
+    "error": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "evidence": {},
+    "head_version": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "header": {},
+    "kind": {
+      "const": "strategy"
+    },
+    "markdown": {
+      "type": "string"
+    },
+    "marks": {
+      "type": "boolean"
+    },
+    "name": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "object": {
+      "type": "string"
+    },
+    "parse_error": {
+      "type": "boolean"
+    },
+    "previous_version": {},
+    "seq": {
+      "type": "integer"
+    },
+    "size": {
+      "type": "string"
+    },
+    "source": {},
+    "status": {},
+    "status_text": {},
+    "structure": {},
+    "url_line": {
+      "type": "string"
+    },
+    "validation": {},
+    "version": {
+      "type": [
+        "integer",
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "markdown"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / what_was_expected
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / workspace_sync
```
Added value: +{
+  "type": "object"
+}
```
removedOutput schema / required
```
Removed value: -[
-  "result"
-]
```
removedOutput schema / x-fastmcp-wrap-result
```
Removed value: -true
```

First observedv0.1.0Jun 13, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only say this is a non-readonly, open-world, non-idempotent, non-destructive write. The description adds real behavioral context beyond that: the original stays unchanged, the copy begins with one version and no backtests, the original retains its versions and backtests, and forking a shared strategy increments its public fork count. This is exactly the kind of disclosure the annotations cannot carry, and it is consistent with destructiveHint=false.

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 dense but front-loaded, leading with the core copy semantics before parenthetical sibling routing. Every clause carries information (copy state, original state, source formats, fork count), though the parenthetical alternative mentions make the first sentence slightly overloaded.

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

Completeness5/5

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

With annotations, a full output schema, and 100% schema coverage, the remaining burden on the description is to explain what happens on invocation and how it differs from neighbors, which it does thoroughly. Nothing an agent needs to call it correctly (source format, copy vs original state, alternatives) is missing.

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?

Schema coverage is already 100%, so the schema documents each parameter's type, bounds, and enum. The description still adds meaning beyond the schema by spelling out that `source` accepts a `str_*` id or a share-link token from any organisation, and by explaining what forking a shared source does. It does not add much for `name`, `present`, `description`, or `target_workspace_id`, which the schema already covers.

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?

States a specific verb and resource (copy/fork a strategy into the caller's org as a separate strategy with its own history) and explicitly contrasts with two siblings: `keel_strategy_compose` for saving a new version and `keel_share_create` for sharing. An agent can distinguish fork from compose/share without opening either schema.

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?

Names the alternative operations and the conditions that select them (saving a new version is compose; sharing is share_create), and clarifies that `source` may be any organisation's share link. It stops short of an explicit 'use this when you want your own editable copy' trigger, so a 4 rather than 5.

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

Deploy Server