parseltongue-claude
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| parseltongue_create_sessionB | Create a new Parseltongue verification session. Args: session_id: Unique identifier for this session (e.g., 'sec-filing-review') Returns: JSON with session creation status |
| parseltongue_register_documentA | Register a source document for evidence grounding. Facts extracted from this document can cite it with :evidence blocks. Args: session_id: Session ID name: Document name (referenced in :evidence blocks) content: Document text content Returns: JSON with registration status |
| parseltongue_load_dslB | Load Parseltongue DSL into the session. Parses facts, axioms, defterms, derives, and diffs. Returns verification status including any quote mismatches (hallucinations). Args: session_id: Session ID dsl_source: Parseltongue DSL source code Returns: JSON with parse status and verification results |
| parseltongue_check_consistencyC | Run full consistency check on the session. Returns detailed report of verified claims, unverified claims (hallucinations), and logical inconsistencies. Args: session_id: Session ID Returns: JSON with consistency check results |
| parseltongue_get_stateB | Get current state of the session. Returns facts, derives, axioms, and their verification status. Args: session_id: Session ID Returns: JSON with session state |
| parseltongue_queryC | Query the system with a well-formed formula (WFF). Args: session_id: Session ID wff: Well-formed formula to evaluate Returns: JSON with query result |
| parseltongue_list_sessionsC | List all active sessions. Returns: JSON with list of sessions |
| parseltongue_clear_sessionA | Clear all state from a session, keeping the session alive. Args: session_id: Session ID Returns: JSON with clear status |
| parseltongue_dsl_referenceB | Get the Parseltongue DSL reference documentation. Returns: Full DSL reference as a string |
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 9 tools
Tools are largely distinct by function: create/register/load/check/query/get/clear each target a different aspect of the session lifecycle. The only mild overlap is parseltongue_check_consistency vs parseltongue_load_dsl (both return verification/consistency info) and get_state vs query, but descriptions make the boundaries reasonably clear.
All tools follow the consistent parseltongue_verb_noun pattern (create_session, register_document, load_dsl, check_consistency, get_state, query, list_sessions, clear_session, dsl_reference). Minor deviation is the verb-less 'query' and 'dsl_reference', but these are readable and predictable overall.
Nine tools is a reasonable count for a session-management plus DSL-engine server. Each tool serves a clear purpose without feeling bulky; slightly on the higher end for a content-verification tool but well within acceptable range.
The surface covers the full session lifecycle: create, register documents, load DSL, check, query, get state, list, and clear. Minor gaps exist (no delete_session/destroy session, no update/append operations), but the core verification workflow is well covered.