// MCP TOOL REFERENCE

CONTENTRAIN TOOLS

19 tools from the Contentrain MCP Server, categorised by risk level.

View the Contentrain policy → Token cost: 4,418 tokens →

// ALL 19 CONTENTRAIN TOOLS

READ 10 tools

Read contentrain_branch_list List pending contentrain (cr/*) branches with their merge status against the contentrain branch. Use this t... Read contentrain_bulk Batch operations on content entries. All operations are auto-committed to git. Read contentrain_content_list List content entries (read-only). Returns data from .contentrain/ — do NOT manually create or modify conten... Read contentrain_describe Get full schema of a single model (read-only). Do NOT manually create content files — use contentrain_conte... Read contentrain_describe_format Describes the Contentrain content file format for any language/platform. Returns a comprehensive specificat... Read contentrain_doctor Project health report (read-only). Returns structured checks: git, node, .contentrain/ structure, model par... Read contentrain_scaffold Template-based project setup. Available templates: blog, landing, docs, ecommerce, saas, i18n, mobile. Chan... Read contentrain_scan Scan project source code for content strings. Three modes: "graph" builds import/component graph for projec... Read contentrain_status Get full project status (read-only). Returns config, models, context. Do NOT manually edit .contentrain/ ba... Read contentrain_validate Validate project content against model schemas. Detects required field violations, type mismatches, broken ...

WRITE 6 tools

Write contentrain_apply Apply normalize operations. Two modes: "extract" writes agent-approved strings to Contentrain content files... Write contentrain_content_save Save content entries. Entry format varies by model kind: DICTIONARY — provide "locale" and "data" (flat key... Write contentrain_init Initialize .contentrain/ structure. Changes are auto-committed to git — do NOT manually create .contentrain... Write contentrain_merge Merge a review-mode branch into contentrain. Local git operation — no external platform needed. Merges the ... Write contentrain_model_save Create or update a model definition. Changes are auto-committed to git — do NOT manually edit .contentrain/... Write contentrain_submit Push contentrain/* branches to remote. MCP is push-only — PR creation is handled by the platform. Do NOT ma...

DESTRUCTIVE 3 tools

Destructive contentrain_branch_delete Delete a pending contentrain (cr/*) branch that will not be merged — e.g. a branch left behind by a failed ... Destructive contentrain_content_delete Delete content entries. For dictionaries, use "keys" to remove specific keys (omit to delete entire locale ... Destructive contentrain_model_delete Delete a model and its content/meta. Changes are auto-committed to git — do NOT manually edit .contentrain/...

// RUNNING THIS SERVER

The managed route: connect Contentrain through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @contentrain/mcp

// FAQ

How many tools does the Contentrain MCP server have? +

The Contentrain MCP server exposes 19 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Contentrain tools? +

Route the Contentrain server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Contentrain tools fall into? +

Contentrain tools are categorised as Read (10), Write (6), Destructive (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.