DevProjex MCP Server

Overview Schema Source Related Servers Discussions Admin

Pack project context

pack_context

Read-only

Builds multi-file project context within a token budget, selecting tree, content, or both so AI agents can analyze large codebases without exceeding limits.

Instructions

Builds multi-file project context. Use it after get_tree, search_project, or analyze; use get_file for one file. Returns inline untrusted project data, or pack_id plus a preview above 50,000 characters for read_pack. Key parameters: detail, view=tree|content|tree-content, format, rank, focus, max_tokens, git_scope, and detail_by_pattern. detail=full still transforms content. expand_related adds resolved selected neighbours. focus requires rank=importance; max_tokens admits greedily by estimate. Last pattern override wins. Project: unique listed name, absolute path returned by list_projects, or #index.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`rank`	No	Orders the selection with importance-v1 and controls max_tokens admission; omission keeps ordinary order and avoids dependency or Git-history work.
`view`	No	Chooses tree, file content, or both for the pack.	tree-content
`focus`	No	Seeds focus-v1 order from 1..16 selected paths; requires rank=importance and never widens selection.
`paths`	No	Narrows selection to literal paths for existing project-relative files or directories; glob characters are ordinary.
`branch`	No	Remote Git branch; invalid for local projects.
`detail`	No	Content transform: full adds no transformations; transformations enabled by the active profile still apply. Compact removes comments and blank lines, and signatures keeps supported code signatures; other languages remain unchanged.	full
`format`	No	Chooses readable markdown/text or structured JSON/XML output.	markdown
`profile`	No	Selection profile: standard uses all eight exclusion toggles plus gitignore; local uses the desktop profile listed by list_projects.profiles; otherwise give a portable profile path inside the project.
`project`	No	unique listed name, absolute path returned by list_projects, or #index.
`git_scope`	No	Narrows to staged, changed (including untracked files), or diff:<ref>..<ref> paths; content stays from the current working tree.
`max_tokens`	No	Sets greedy content admission; document structure and its report are outside this heuristic token budget.
`tracked_only`	No	Restricts results to Git-tracked files; accepts a boolean or its string form.
`expand_related`	No	Adds resolved neighbours of seed files without widening filters or Git scope; stops at 400 files and reports the limit.
`max_file_bytes`	No	Excludes selected files larger than this byte count; accepts an integer or numeric string.
`exclude_patterns`	No	Removes paths with the same project-relative glob syntax as include_patterns.
`include_patterns`	No	Narrows with project-relative '/' globs: '' and '?' stay in one segment, '*/' spans depths, and '{a,b}' alternates; matching is case-sensitive, while '!' and '[...]' are rejected.
`detail_by_pattern`	No	Overrides detail by file in array order; the last match wins, never widens selection, and unmatched or invalid entries are reported.

Schema Changelog

Changes observed during successful MCP inspections.

Changed29 schema fields changedv5.2.0Oct 3, 2026

changedInput schema / properties / branch / description

Previous value: -"Optional Git branch for a remote project URL; invalid for local project paths."New value: +"Remote Git branch; invalid for local projects."

changedInput schema / properties / detail / description

Previous value: -"Collapse code to signatures or strip comments/blank lines to fit large projects into a budget; unsupported languages are returned unchanged."New value: +"Content transform: full adds no transformations; transformations enabled by the active profile still apply. Compact removes comments and blank lines, and signatures keeps supported code signatures; other languages remain unchanged."

addedInput schema / properties / detail_by_pattern

Added value: +{
+  "description": "Overrides detail by file in array order; the last match wins, never widens selection, and unmatched or invalid entries are reported.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "detail": {
+        "enum": [
+          "full",
+          "compact",
+          "signatures"
+        ],
+        "type": "string"
+      },
+      "patterns": {
+        "description": "Uses the include_patterns glob syntax.",
+        "items": {
+          "maxLength": 512,
+          "minLength": 1,
+          "type": "string"
+        },
+        "maxItems": 32,
+        "minItems": 1,
+        "type": "array"
+      }
+    },
+    "required": [
+      "patterns",
+      "detail"
+    ],
+    "type": "object"
+  },
+  "maxItems": 16,
+  "type": "array"
+}

changedInput schema / properties / exclude_patterns / description

Previous value: -"Project-relative glob patterns using '/' to exclude additional paths."New value: +"Removes paths with the same project-relative glob syntax as include_patterns."

removedInput schema / properties / exclude_patterns / items

Removed value: -{
-  "maxLength": 512,
-  "minLength": 1,
-  "type": "string"
-}

removedInput schema / properties / exclude_patterns / maxItems
```
Removed value: -256
```

addedInput schema / properties / exclude_patterns / oneOf

Added value: +[
+  {
+    "maxLength": 512,
+    "minLength": 1,
+    "type": "string"
+  },
+  {
+    "items": {
+      "maxLength": 512,
+      "minLength": 1,
+      "type": "string"
+    },
+    "maxItems": 256,
+    "type": "array"
+  }
+]

removedInput schema / properties / exclude_patterns / type
```
Removed value: -"array"
```

addedInput schema / properties / expand_related

Added value: +{
+  "additionalProperties": false,
+  "description": "Adds resolved neighbours of seed files without widening filters or Git scope; stops at 400 files and reports the limit.",
+  "properties": {
+    "direction": {
+      "default": "both",
+      "description": "Traversal direction, matching related_files.",
+      "enum": [
+        "dependencies",
+        "dependents",
+        "both"
+      ],
+      "type": "string"
+    },
+    "hops": {
+      "default": 1,
+      "description": "Number of edges to follow from each seed.",
+      "maximum": 2,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "seeds": {
+      "description": "Selected project-relative seed files; directories and globs are invalid.",
+      "items": {
+        "type": "string"
+      },
+      "maxItems": 16,
+      "minItems": 1,
+      "type": "array"
+    }
+  },
+  "required": [
+    "seeds"
+  ],
+  "type": "object"
+}

addedInput schema / properties / focus

Added value: +{
+  "description": "Seeds focus-v1 order from 1..16 selected paths; requires rank=importance and never widens selection.",
+  "oneOf": [
+    {
+      "maxLength": 4096,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "maxLength": 4096,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 16,
+      "minItems": 1,
+      "type": "array"
+    }
+  ]
+}

addedInput schema / properties / format / description

Added value: +"Chooses readable markdown/text or structured JSON/XML output."

changedInput schema / properties / git_scope / description

Previous value: -"Further restrict results to staged files, all current changes, or files changed between two Git refs."New value: +"Narrows to staged, changed (including untracked files), or diff:<ref>..<ref> paths; content stays from the current working tree."

changedInput schema / properties / include_patterns / description

Previous value: -"Project-relative glob patterns using '/'. They only narrow built-in and gitignore filtering."New value: +"Narrows with project-relative '/' globs: '*' and '?' stay in one segment, '**/' spans depths, and '{a,b}' alternates; matching is case-sensitive, while '!' and '[...]' are rejected."

removedInput schema / properties / include_patterns / items

Removed value: -{
-  "maxLength": 512,
-  "minLength": 1,
-  "type": "string"
-}

removedInput schema / properties / include_patterns / maxItems
```
Removed value: -256
```

addedInput schema / properties / include_patterns / oneOf

Added value: +[
+  {
+    "maxLength": 512,
+    "minLength": 1,
+    "type": "string"
+  },
+  {
+    "items": {
+      "maxLength": 512,
+      "minLength": 1,
+      "type": "string"
+    },
+    "maxItems": 256,
+    "type": "array"
+  }
+]

removedInput schema / properties / include_patterns / type
```
Removed value: -"array"
```

changedInput schema / properties / max_file_bytes / description

Previous value: -"Exclude otherwise selected files strictly larger than this byte count; integer or numeric string."New value: +"Excludes selected files larger than this byte count; accepts an integer or numeric string."

changedInput schema / properties / max_tokens / description

Previous value: -"Maximum estimated content tokens to include; accepts an integer or numeric string. Document structure is outside this budget."New value: +"Sets greedy content admission; document structure and its report are outside this heuristic token budget."

changedInput schema / properties / paths / description

Previous value: -"Existing project-relative files or directories that narrow the selection."New value: +"Narrows selection to literal paths for existing project-relative files or directories; glob characters are ordinary."

removedInput schema / properties / paths / items

Removed value: -{
-  "maxLength": 4096,
-  "minLength": 1,
-  "type": "string"
-}

removedInput schema / properties / paths / maxItems
```
Removed value: -256
```

addedInput schema / properties / paths / oneOf

Added value: +[
+  {
+    "maxLength": 4096,
+    "minLength": 1,
+    "type": "string"
+  },
+  {
+    "items": {
+      "maxLength": 4096,
+      "minLength": 1,
+      "type": "string"
+    },
+    "maxItems": 256,
+    "type": "array"
+  }
+]

removedInput schema / properties / paths / type
```
Removed value: -"array"
```

changedInput schema / properties / profile / description

Previous value: -"Selection profile: 'standard', 'local', or a portable profile JSON path inside the project root."New value: +"Selection profile: standard uses all eight exclusion toggles plus gitignore; local uses the desktop profile listed by list_projects.profiles; otherwise give a portable profile path inside the project."

changedInput schema / properties / project / description

Previous value: -"Absolute root path returned by list_projects, or a Git URL when the server allows remote sources. Optional only when one local root is configured."New value: +"unique listed name, absolute path returned by list_projects, or #index."

addedInput schema / properties / rank

Added value: +{
+  "description": "Orders the selection with importance-v1 and controls max_tokens admission; omission keeps ordinary order and avoids dependency or Git-history work.",
+  "enum": [
+    "importance"
+  ],
+  "type": "string"
+}

changedInput schema / properties / tracked_only / description

Previous value: -"Restrict results to files tracked by Git; accepts a boolean or the string 'true' or 'false'."New value: +"Restricts results to Git-tracked files; accepts a boolean or its string form."

addedInput schema / properties / view / description

Added value: +"Chooses tree, file content, or both for the pack."

First observedv5.1.0Sep 8, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnly=true, destructive=false, openWorld=false, so the safety profile is covered. The description adds genuinely new behavioral context: output is inline 'untrusted project data', there is a 50,000-character threshold that switches the return to pack_id plus preview, and 'detail=full still transforms content'. Some rules it repeats (focus requires rank, greedy admission, last-match-wins) are already in the schema, which keeps this from a 5.

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

Conciseness3/5

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

Purpose and routing are correctly front-loaded, but the closing 'Key parameters: ...' enumeration and the 'Project: unique listed name...' clause duplicate a 100%-covered schema verbatim, which is waste rather than conciseness. The semicolon-chained cross-parameter rules are also hard to parse in a single breath.

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 17-parameter tool with nested objects and no output schema, the description covers the essentials: what it produces, the inline-vs-pack_id return split, and the routing to read_pack and get_file. It stops short of describing selection/ordering behavior in depth, but with 100% schema coverage that gap is minor.

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 all 17 parameters are already documented in the schema, including cross-parameter rules like 'requires rank=importance' and 'last match wins'. The description's parameter list and the 'Project:' clause largely restate the schema, adding no syntax or semantics the schema lacks. Baseline 3 is correct when the schema does the heavy lifting.

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 opening sentence states a specific verb+resource ('Builds multi-file project context') and immediately contrasts with the sibling it is not: 'use get_file for one file.' An agent can distinguish it from get_tree, search_project, analyze and get_file without opening a schema.

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

Usage Guidelines5/5

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

Explicit sequencing guidance is given ('Use it after get_tree, search_project, or analyze'), the alternative for single files is named (get_file), and the downstream handoff is spelled out (pack_id plus preview above 50,000 characters for read_pack). Both when-to-use and which-other-tool conditions are covered.

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

Deploy Server

Pack project context

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools