Synthesized post-cutoff answer with inline citations. Use this when your model is small / cheap / weaker at tool-result synthesis (Llama, Gemini Flash, Mistral, Nemotron, Qwen). Fillin runs a server-side LLM pass over the retrieved post-cutoff documents and returns a 150-250 word answer with [tit...
Risk signalsAccepts freeform code/query input (query)
Part of the Fillin server.
Free to start. No card required.
AI agents use fillin_answer to create or modify resources in Fillin. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call fillin_answer repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Fillin.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"fillin_answer": {
"limits": [
{
"counter": "fillin_answer_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Fillin policy for all 11 tools.
These attack patterns abuse exactly the kind of access fillin_answer gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Synthesized post-cutoff answer with inline citations. Use this when your model is small / cheap / weaker at tool-result synthesis (Llama, Gemini Flash, Mistral, Nemotron, Qwen). Fillin runs a server-side LLM pass over the retrieved post-cutoff documents and returns a 150-250 word answer with [title](url) citations already embedded — you can quote it directly. Premium models (Opus, Sonnet, GPT-4o) usually get better results from fillin_query and synthesizing themselves, but this tool works for any caller. Costs more than fillin_query because of the synthesis pass. Returns: A dict with: - answer: the synthesized paragraph (str | None) - citations: list of {title, url} extracted from the answer - corpus_match: "strong" | "weak" | "none" — quality of retrieval - top_score: float — top reranked similarity score - model: the synthesizer model used (e.g. claude-haiku-4-5) - reason: set when answer is None (e.g. "no_relevant_docs") - results: raw post-cutoff documents (same shape as fillin_query) - cutoff, query, gap_days: echoes for context. It is categorised as a Write tool in the Fillin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fillin MCP server in PolicyLayer and add a rule for fillin_answer: 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 Fillin. Nothing to install.
fillin_answer 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 fillin_answer 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 fillin_answer. 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.
fillin_answer is provided by the Fillin MCP server (https://fillin.glyphapi.dev/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Fillin tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.