Skip to main content
Glama

Nullcone Threat Intelligence

by io.github.maco144

check_prompt

Check a prompt or text fragment for known PROMPT IOC patterns.

Uses an in-memory hash set for sub-1ms token-level querying — no
network calls after the cache is warmed. Slides a window of 3, 5, 8,
and 10 tokens across the input and checks each window's canonical
SHA256 against the PROMPT IOC feed.

This is the primary real-time prompt injection detection endpoint.
Call it on every user-supplied prompt before passing to the LLM.

Args:
    text:      The prompt text to check (raw, any length)
    auto_warm: If True and cache is empty, warm it first (adds ~300ms
               on first call only). Default True.

Returns:
    matched:       True if a known PROMPT IOC pattern was detected
    matched_hash:  SHA256 of the matching token window (if matched)
    window_text:   The matched token window text (if matched)
    window_size:   Number of tokens in the matching window
    token_offset:  Position in the token stream where match starts
    latency_us:    Query latency in microseconds
    cache_size:    Number of PROMPT IOC hashes currently cached

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
auto_warmNo

TDQS

A4.5/5.0
Behavior5/5

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

With zero annotations, the description carries the full burden and exceeds it — disclosing the in-memory hash set mechanism, sub-1ms latency, no-network-after-warm behavior, sliding window sizes (3/5/8/10), canonical SHA256 hashing, and the ~300ms first-call warm penalty. It even documents latency_us and cache_size as return diagnostics, giving the agent a complete behavioral model.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight paragraphs with a clean Returns list for machine/agent parsing. Every sentence earns its place — mechanism, usage directive, params, return contract. It borders on verbose for an API description, but the density is justified for the behavioral richness it conveys. The monospaced Args/Returns formatting provides scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-param tool with no output schema, the description covers all the essential bases: what, when, how, parameters, and a complete 7-field Returns section (matched, matched_hash, window_text, window_size, token_offset, latency_us, cache_size). The only gaps are edge behavior, such as what happens with empty input or error conditions, which is a minor omission for an otherwise thorough contract.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate — and it does. Both params are documented: text as 'raw, any length' and auto_warm with the crucial cost-benefit note ('adds ~300ms on first call only'). The auto_warm clarification adds genuine value about a performance tradeoff the boolean schema type could never convey. Slight deduction because this critical info is embedded in prose rather than structured, making it easier for an agent to miss.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with 'Check a prompt or text fragment for known PROMPT IOC patterns' — a precise verb+resource+domain statement. 'This is the primary real-time prompt injection detection endpoint' explicitly positions it against the sibling check_prompt_batch, distinguishing it as the real-time variant. No ambiguity about what this tool does.

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

Usage Guidelines4/5

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

Gives an explicit directive: 'Call it on every user-supplied prompt before passing to the LLM.' The phrase 'primary real-time... endpoint' implicitly differentiates from the batch sibling, but it never explicitly names check_prompt_batch as the alternative or states when NOT to use this tool, leaving the when-vs-batch guidance slightly implicit.

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

All Nullcone Threat Intelligence toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, but there is notable overlap among threat-fetching methods: get_new_threats, poll_since, and drain_subscription all retrieve new threats via different mechanisms, and several stats tools (get_stats, freshness_limits, prompt_cache_stats) serve similar informational roles. Overall, descriptions help disambiguate, but a few tools could be confused.

Naming Consistency3/5

The naming is predominantly snake_case, but mixes verb_noun (check_freshness, submit_ioc), noun phrases (family_threats, freshness_limits), and even a question (is_ioc_revoked). 'unsubscribe' breaks the pattern of other subscription tools (subscribe_threats, drain_subscription). This inconsistency is noticeable though still readable.

Tool Count3/5

30 tools is on the heavy side for a single MCP server, exceeding the typical 15-tool comfort zone. However, the server covers a broad domain—IOC submission, retrieval, subscriptions, freshness tracking, prompt/skill scanning, and registry monitoring—so the large number is somewhat justified by the scope.

Completeness4/5

The tool surface covers the full threat intelligence lifecycle: submit (submit_ioc, submit_batch), query (lookup_ioc, search_by_type, recent_threats, family_threats), subscribe (subscribe_threats, drain_subscription), update (report_detection, vote_false_positive), and revoke (revoke_ioc). Minor gaps exist, such as the absence of a direct delete or update signature tool and no get-by-signature-id endpoint, but these are manageable for agents.

Resources