Skip to main content
Glama
S2thend

cursor-history-mcp

by S2thend
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

cursor_history_export

Export a Cursor AI chat session to Markdown or JSON for sharing, backup, or analysis. Choose a session by ID or list index and get formatted content ready to use.

Instructions

Export a Cursor AI chat session to Markdown or JSON format. Returns the formatted content.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
formatNoExport format: 'markdown' for human-readable, 'json' for structured datamarkdown
sessionIdNoExact native session UUID returned by list/search. Case-sensitive; do not normalize.
workspaceNoWorkspace path. Reuse the same scope for listing and reading a session index.
sessionIndexNoOne-based index from a list with the same workspace scope. Prefer sessionId for reuse.
includeCrossWorkspaceSourcesNoOpt in to complementary sources outside this workspace, only for already selected session IDs. Default: false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.3.1
    • addedInput schema / oneOf
      Added value: +[
+  {
+    "not": {
+      "required": [
+        "sessionId"
+      ]
+    },
+    "required": [
+      "sessionIndex"
+    ]
+  },
+  {
+    "not": {
+      "required": [
+        "sessionIndex"
+      ]
+    },
+    "required": [
+      "sessionId"
+    ]
+  }
+]
    • addedInput schema / properties / includeCrossWorkspaceSources
      Added value: +{
+  "default": false,
+  "description": "Opt in to complementary sources outside this workspace, only for already selected session IDs. Default: false.",
+  "type": "boolean"
+}
    • addedInput schema / properties / sessionId
      Added value: +{
+  "description": "Exact native session UUID returned by list/search. Case-sensitive; do not normalize.",
+  "minLength": 1,
+  "type": "string"
+}
    • changedInput schema / properties / sessionIndex / description
      Previous value: -"The session index (1-based, as shown in list output)"New value: +"One-based index from a list with the same workspace scope. Prefer sessionId for reuse."
    • addedInput schema / properties / workspace
      Added value: +{
+  "description": "Workspace path. Reuse the same scope for listing and reading a session index.",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "sessionIndex"
-]
  2. First observedv0.2.4

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations, the description must fully disclose behavior. It only states 'Returns the formatted content', which clarifies the output but omits any side effects (e.g., whether a file is saved), how session selection works (sessionId vs sessionIndex), workspace scope requirements, or any limits. For a complex tool with a oneOf constraint, this is insufficient.

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 one concise sentence that gets straight to the point: what the tool does and the output format. No filler, no repetition. It is appropriately sized for its purpose.

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

Completeness2/5

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

The tool has 5 parameters, a oneOf requirement (sessionId XOR sessionIndex), and no output schema or annotations. The description leaves out critical context: how to choose between sessionId and sessionIndex, that workspace must match the listing scope, that includeCrossWorkspaceSources is opt-in, and what errors might occur. The schema covers parameter-level details, but the overall tool behavior is under-described.

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 baseline is 3. The description echoes the format options (Markdown/JSON) already documented in the schema but adds no new semantics about parameters. The phrase 'formatted content' is a trivial restatement of the schema's 'human-readable' for markdown and 'structured data' for JSON. No value beyond the schema is provided.

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 uses a specific verb ('Export') and a clear resource ('Cursor AI chat session'), and names the exact output formats (Markdown or JSON). This distinguishes it from siblings like cursor_history_backup and cursor_history_show, which imply different operations. The purpose is unambiguous and immediately understandable.

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?

The description gives no guidance on when to use this tool versus siblings such as cursor_history_show or cursor_history_backup. It does not state any prerequisites, exclusions, or typical usage scenarios. The only hint is the word 'Export', which weakly implies a file-producing intent, but nothing explicit is provided.

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