Signature feature: structural continuity check using the configured open-source model (CELIUMS_LLM_MODEL, routed via Atlas — never a closed model). Loads the target scene, prior 20 scenes, all characters (with their secrets_known_at_chapter and voice samples), and worldbuilding rules. Outputs a J...
AI agents use write_continuity_check to create or update resources in Celiums Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Celiums Memory environment.
This tool performs analysis and generates recommendations for writing content (detecting secret-leaks, description-drift, timeline conflicts, etc.) and provides suggested fixes. While it reads extensively (prior scenes, character data, worldbuilding rules), its primary function is to produce structured feedback that informs or guides writing revisions.
From the tool's definition Tool description explicitly states it 'Outputs a JSON list of issues' with 'suggested_fix' and loads/analyzes writing structure. This is content analysis and modification suggestion, not execution of arbitrary operations or deletion.
Documented attack patterns abuse exactly the kind of access write_continuity_check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Celiums Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for write_continuity_check:
{
"version": "1",
"default": "deny",
"tools": {
"write_continuity_check": {
"limits": [
{
"counter": "write_continuity_check_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}write_continuity_check stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Signature feature: structural continuity check using the configured open-source model (CELIUMS_LLM_MODEL, routed via Atlas — never a closed model). Loads the target scene, prior 20 scenes, all characters (with their secrets_known_at_chapter and voice samples), and worldbuilding rules. Outputs a JSON list of issues: secret-leak, description-drift, timeline conflict, worldbuilding violation, voice drift. Each issue includes severity, scene_position, description, and a suggested_fix. NO other writing tool does this — Sudowrite/Grammarly/ProWritingAid are line-by-line, this is structural. It is categorised as a Write tool in the Celiums Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for write_continuity_check: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Celiums Memory. Nothing to install.
write_continuity_check is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the write_continuity_check rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for write_continuity_check. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
write_continuity_check is provided by the Celiums Memory MCP server (terrizoaguimor/celiums-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Celiums Memory, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
62 Celiums Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.