Update existing links between sources and entities.
AI agents use update_entity_links to create or update resources in literateMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your literateMCP environment.
This tool modifies data (relationship links) reversibly without deleting or destroying data, and does not execute arbitrary code or move money. It fits the Write category. Severity is medium because a misused link update could corrupt the knowledge graph organization of academic literature, but the operation is reversible and confined to link metadata rather than source or entity content itself.
From the tool's definition Tool description states 'Update existing links between sources and entities' — the verb 'update' indicates modification of relationships in the database.
Documented attack patterns abuse exactly the kind of access update_entity_links gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and literateMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for update_entity_links:
{
"version": "1",
"default": "deny",
"tools": {
"update_entity_links": {
"limits": [
{
"counter": "update_entity_links_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_entity_links 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.
Update existing links between sources and entities. It is categorised as a Write tool in the literateMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the literate MCP server in PolicyLayer and add a rule for update_entity_links: 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 literateMCP. Nothing to install.
update_entity_links 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 update_entity_links 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 update_entity_links. 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.
update_entity_links is provided by the literate MCP server (zongmin-yu/sqlite-literature-management-fastmcp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from literateMCP, 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.
15 literateMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.