Legalithm
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LEGALITHM_TELEMETRY | No | Set to 0 to disable anonymous usage telemetry. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| classifyA | Classify an AI use case under the EU AI Act — risk tier + cited rationale. Offline; checked against Regulation (EU) 2024/1689, not legal advice. |
| explain_obligationA | List the EU AI Act obligations for a role + risk tier, each with its Article citation. Pass country (and sector) to also get the competent national authority. Offline. |
| generate_disclosureA | Generate an Article 50 transparency disclosure snippet (chatbot / genai-content / deepfake / emotion), EN or DE. Offline. |
| check_recordA | Fetch a published Legalithm Trust Center compliance record by org slug. Online (reads the public API). |
| generate_agent_disclosureA | Draft the Article 50(1) disclosure an AI agent owes: what it is, who it acts for, and the limits of its delegated authority. Follows the Commission Article 50 Guidelines adopted 20 July 2026. Refuses rather than inventing a principal. Offline. |
| discover_ai_surfacesA | Reads file CONTENT you pass in (a package.json, source files) and proposes which AI capabilities the code could ship, with the evidence for each, then resolves those into Article 50 limbs with their dates and duty-bearers. Returns HYPOTHESES, never findings: a dependency proves what code could do, never what it ships. Offline, no network, nothing stored. |
| agent_disclosure_taxonomyA | The six disclosure dimensions an AI agent owes under Article 50(1), plus the negative scope: what the Commission Guidelines confirm is NOT covered, including chain-of-thought, backend machine-to-machine calls and agent-to-agent traffic. Offline. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool addresses a distinct task: classification, obligation lookup, disclosure generation, agent-specific disclosure, code-surface discovery, taxonomy reference, and record lookup. The mild ambiguity between generate_disclosure and generate_agent_disclosure is resolved by their clear scope descriptions, so agents should rarely misselect.
Six of seven tools follow a clear verb_noun snake_case pattern: classify, explain_obligation, generate_disclosure, check_record, generate_agent_disclosure, and discover_ai_surfaces. agent_disclosure_taxonomy breaks the verb convention by starting with a noun, but it is still consistent in style and predictable.
Seven tools is well-scoped for an EU AI Act compliance assistant: classification, obligations, disclosure generation, agent disclosure, code analysis, taxonomy reference, and record lookup. Each tool earns its place, and the count is neither bloated nor thin.
The core workflow—classify a use case, look up obligations, generate the correct disclosure, analyze code surfaces, and check a compliance record—is covered. Minor gaps exist, such as no create/update path for Trust Center records and no broader EU AI Act article search, but agents can complete the main intended tasks without dead ends.