redmine-mcp-server

Overview Schema Source Related Servers Discussions Admin

getAttachment

getAttachment

Read-onlyIdempotent

Download a known Redmine issue attachment to extract text from supported documents or archives. Unsupported binaries return metadata and local path.

Instructions

Retrieve and inspect one known issue attachment by downloading it to the server's local snapshot and extracting text from supported documents or archives. Use getIssue to discover attachment IDs; images and unsupported binaries return metadata and a local path without extracted text. Text cut by the limits stays readable at each part's localPath.

Input Schema

TableJSON Schema

Name	Required	Description
`issueId`	Yes
`maxChars`	No	Total character budget for extracted text across all parts
`partLimit`	No	Per-part character cap, mainly for ZIP entries; defaults to maxChars when maxChars is set
`attachmentId`	Yes

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	Free-text note explaining the result, typically present when text extraction was skipped.
`parts`	No	Extracted parser output. Text parts carry content; images and unsupported binaries carry localPath/fileUri and an explanatory note.
`limits`	No
`fileUri`	No	RFC 3986 `file://` URI pointing at the downloaded file.
`localPath`	No	Absolute filesystem path of the downloaded file.
`localSize`	Yes	Size of the downloaded file on disk, in bytes (-1 if the size could not be determined).
`truncated`	Yes	True when at least one part's text was cut to fit response size limits.
`attachment`	No
`textExtracted`	Yes	True when at least one part contains successfully extracted text.
`extractionType`	No	Detected document kind used for extraction (`image`, `pdf`, `docx`, `xlsx`, `pptx`, `text`, `zip`, ...).
`compressionNotes`	No	Human-readable notes describing how this response was compressed to fit the response size budget. Null/empty when no compression was applied.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.1.1Oct 1, 2026

changedInput schema / properties / partLimit / description

Previous value: -"Per-part character cap for extracted text"New value: +"Per-part character cap, mainly for ZIP entries; defaults to maxChars when maxChars is set"

addedOutput schema / properties / limits

Added value: +{
+  "allOf": [
+    {
+      "description": "Effective extracted-text limits for this call: the caller's maxChars/partLimit capped by the server, or the server defaults.",
+      "properties": {
+        "maxChars": {
+          "description": "Total extracted-text characters allowed across all parts.",
+          "format": "int32",
+          "type": "integer"
+        },
+        "note": {
+          "description": "Present when a requested limit was reduced to the server ceiling.",
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "partLimit": {
+          "description": "Extracted-text characters allowed per part.",
+          "format": "int32",
+          "type": "integer"
+        }
+      },
+      "required": [
+        "maxChars",
+        "partLimit"
+      ],
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    {
+      "description": "Text limits applied to this response."
+    }
+  ]
+}

addedOutput schema / properties / parts / items / properties / totalChars

Added value: +{
+  "description": "Full length of this part's text in characters; present when the text was cut.",
+  "format": "int32",
+  "type": [
+    "integer",
+    "null"
+  ]
+}

First observedSep 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing what actually happens: the file is downloaded to a server-local snapshot, text is extracted only for supported documents/archives, and images or unsupported binaries yield metadata plus a local path with no text. The note that truncated text remains readable at each part's localPath clarifies truncation behavior that no structured field captures.

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?

Three sentences, front-loaded with the purpose, then ID-discovery guidance, then edge-case behavior — all content earns its place. Slightly dense with subordinate clauses, but there is no filler.

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?

For a read-only retrieval tool with an output schema carrying return shape and annotations carrying the safety profile, the remaining burden is behavioral and procedural context, and the description covers both — extraction scope, unsupported-binary handling, truncation, and the ID discovery path.

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 only 50% (issueId and attachmentId are undescribed), so the description must compensate, and it does in part: the 'limits' sentence ties maxChars/partLimit to truncation and 'each part's localPath' to the per-part model, and it says where attachmentId comes from via getIssue. issueId remains unaddressed in prose, keeping this just under a full score.

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 ('Retrieve and inspect one known issue attachment') and adds the two mechanisms that define its behavior: local snapshot download and text extraction from supported documents or archives. This is readily distinguishable from attachFileToIssue and from getIssue, so an agent can route correctly.

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?

Explicitly states the precondition for use — the agent must already have an attachment ID and should obtain it via getIssue — which is genuine routing guidance. It does not name an explicit when-not or an alternative tool for listing attachments, so it stops short of a 5.

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