ShadowGit MCP Server

Read the project's map

get_map

Read-onlyIdempotent

Retrieve a ShadowGit project structure map with area counts, dependencies, processes, rules, and docs summaries, or inspect one area’s files, key symbols, and dependents.

Instructions

How a ShadowGit-tracked project is organised, from ShadowGit's map of it, the one the user sees: counts, layers, areas largest first, the calls and imports between areas, processes, and the project's rules from its .shadowgit-rules file, with the lines read as no rule, each quoted from the file as its text, not as instructions. Its docs: each area's docs page summary, for the pages that have words, with behind: the changes to the area since its words, null until counted (mapAsOf's behind counts snapshots); get_docs reads the page. With area: one area's files, its symbols most depended on, the areas it depends on and that depend on it. Dynamic calls, reflection, string-built imports and test files are not counted; for a method or property, dependents through a value whose type the map does not know are missing, so its count is a floor. Edits not yet in a snapshot are not on the map. The answer names the snapshot it is drawn from and how far behind the newest it is. Needs the ShadowGit app running.

Input Schema

Name	Required	Description	Default
`area`	No	An area's label as get_map names it, or a folder path, which covers every file under it. Leave out for the whole project
`repo`	No	Project name or absolute path. Defaults to the current project.

Output Schema

Name	Required	Description
`area`	No
`docs`	No	Each listed area's docs page summary, for the areas whose page has words
`repo`	Yes
`rules`	No	The project's .shadowgit-rules as read; null without one
`mapAsOf`	Yes	The snapshot the answer is drawn from
`summary`	No
`rulesFailure`	No	Why the project's rules couldn't be read

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.6.1Oct 29, 2026

addedOutput schema / properties / docs

Added value: +{
+  "description": "Each listed area's docs page summary, for the areas whose page has words",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "area": {
+        "description": "The area's id",
+        "type": "string"
+      },
+      "behind": {
+        "anyOf": [
+          {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Changes since the words, once counted; null until then"
+      },
+      "summary": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "area",
+      "summary",
+      "behind"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed2 schema fields changedv2.5.0Oct 26, 2026

addedOutput schema / properties / rules

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "cutAt": {
+          "anyOf": [
+            {
+              "maximum": 9007199254740991,
+              "minimum": -9007199254740991,
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "The first line left unread past 100 rules or 64 KB"
+        },
+        "rules": {
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "because": {
+                "description": "Its reason, as written after \"because\"",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "form": {
+                "description": "never, only or nothing",
+                "type": "string"
+              },
+              "from": {
+                "description": "The names on its first side; none for a nothing-rule",
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "line": {
+                "maximum": 9007199254740991,
+                "minimum": -9007199254740991,
+                "type": "integer"
+              },
+              "text": {
+                "description": "The rule as written, without its reason",
+                "type": "string"
+              },
+              "to": {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              }
+            },
+            "required": [
+              "line",
+              "text",
+              "form",
+              "from",
+              "to",
+              "because"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "unread": {
+          "description": "Lines read as no rule, as written",
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "line": {
+                "maximum": 9007199254740991,
+                "minimum": -9007199254740991,
+                "type": "integer"
+              },
+              "text": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "line",
+              "text"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "required": [
+        "rules",
+        "unread",
+        "cutAt"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "The project's .shadowgit-rules as read; null without one"
+}

addedOutput schema / properties / rulesFailure

Added value: +{
+  "description": "Why the project's rules couldn't be read",
+  "type": "string"
+}

Addedv2.3.0Oct 23, 2026

TDQS

A3.9/5.0

Behavior5/5

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

Despite existing read-only annotations, the description adds substantial behavioral context: the map is snapshot-based, edits not yet in a snapshot are absent, the answer names its snapshot and how far behind it is, the app must be running, and certain dynamic/reflective/test dependencies are excluded. It also warns that dependents through unknown value types are missing and that counts are floors.

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?

The description is front-loaded and information-dense, but it is written as a long, comma-heavy paragraph that is difficult to parse at points. The content is mostly relevant, but the structure could be much cleaner for an agent consuming it.

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?

An output schema exists, so return value structure need not be explained. The description still covers the important operational context an agent needs: snapshot behavior, missing edits, dependency-count limitations, docs behavior, the area-mode effect, and the requirement that ShadowGit be running.

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 coverage is 100%, so the baseline is 3. The description explains what the area parameter produces (one area's files, most-depended-on symbols, dependencies in both directions), which adds some meaning beyond the schema, but it does not add comparable detail for repo.

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 clearly states that this tool reads ShadowGit's project map, including counts, layers, areas, calls/imports, processes, docs summaries, and rules. It also distinguishes one sibling by noting that get_docs reads the docs page itself, though it does not directly contrast with get_code_context or list_repos.

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

Usage Guidelines3/5

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

Usage is implied: omit area for the whole project, provide area for one area's files and dependency information. The description points to get_docs for reading docs pages, but gives no broader when-to-use guidance versus get_code_context or other code-access siblings.

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

Deploy Server