rupturetrace-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TA2_MODEL | No | Model identifier used as the default for the `model` tool argument in backend mode. | |
| TA2_ENDPOINT | No | Complete chat-completions endpoint used as the default for the `endpoint` tool argument in backend mode. | |
| OPENAI_API_KEY | No | API key for an OpenAI-compatible backend, read from the environment variable named by `key_env` (default). | |
| DASHSCOPE_API_KEY | No | API key for a Qwen backend, read from the environment variable named by `key_env` when using Qwen. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
RuptureTrace: relation-guided assessment and reassessment of scientific claims. Each claim is rated on a 5-level whole-claim ordinal rubric (-2..+2) while 12 evidence relations (sources->rationale, protocol->claim, results->claim, ...) are audited over three rounds (K0 initial, K1 relation audit, K2 verification). The server tracks support changes and graph zigzag H1 persistence to pick one relation for focused repair, then reassesses the whole claim. Use assess_claim when a model endpoint is configured; otherwise use start_host_assessment and answer each round yourself with submit_host_round. Call describe_protocol for the schema.
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| describe_protocolA | Return the RuptureTrace protocol: rubric, the 12 audited relations, allowed statuses, the per-round JSON output schema, model instructions and the fixed scoring policy. |
| diagnose_roundsA | Compute the prefix diagnosis from three already-produced rounds (K0, K1, K2) without calling any model. Each round must match describe_protocol().round_output_schema. Returns the selected relation for RuptureTrace repair, the local (weakest-support) and without-H1 choices, and every relation's score components and H1 intervals. External quotes are only verified when allow_source_fetch is true. |
| compute_zigzag_h1B | Exact zigzag H1 persistence over GF(2) for an evolving graph. snapshots: ordered edge-ID sets K_0..K_T; edges: [u, v] endpoints per edge ID; n_vertices: vertex count. Uses the diagram K_0 -> K_0 U K_1 <- K_1 -> ... and returns Betti-1 per node and the interval barcode. |
| verify_runA | Verify a RuptureTrace output directory offline: recompute diagnostics, derived files and hashes. Checks record consistency only - not scientific truth. input_path optionally points to the original claim JSONL to check claim/ID linkage. Runs produced in host mode cannot be replay-verified. |
| evaluate_runB | Evaluate a verified run against gold labels (MAE/MSE/Exact, initial-error AUROC, optional localization). results_path must be <run_dir>/ta2_claim_results.jsonl; gold rows need problem_id and gold_label or likert_score in {-2..2}. The JSON report is written to out_path (outside the run directory) and returned. |
| assess_claimB | Run the full RuptureTrace pipeline on one claim using a configured model backend (7 model calls; 9 with ablation). model/endpoint default to the TA2_MODEL / TA2_ENDPOINT environment variables; the API key is read from the environment variable named by key_env (default OPENAI_API_KEY for http, DASHSCOPE_API_KEY for qwen) and is never passed as an argument. If out_dir is given, the complete verifiable artifact directory is written there. Returns a summary (labels, selected relation, top relation scores, rationales). |
| assess_claims_batchB | Run many claims sequentially and write a complete, verifiable run directory to out_dir. Provide either input_path (JSONL rows with claim and optional problem_id / problem_version) or a list of claim strings. Returns the run summary plus one compact row per completed claim. |
| start_host_assessmentA | Start a RuptureTrace assessment where YOU (the MCP client model) produce each round. Returns the first stage prompt (instructions, input payload and output schema). Answer every step with submit_host_round until status is 'completed' (7 steps; 9 with ablation). The server computes support, zigzag H1 persistence and the repair relation itself. If out_dir is set, artifacts are written at the end. |
| submit_host_roundA | Submit your JSON answer for the current step of a host-mode assessment. round_output must contain label (-2..2), confidence (0..1), rationale, assessment_scope='whole_claim' and checks (all 12 relations once, each with relation_id, status, reason, evidence[{kind, source, quote}]). Returns the next stage prompt, or the final summary once all steps are done. Invalid rounds are rejected without advancing, so you can fix and resubmit. |
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
The tools target clearly separable stages: single vs batch assessment, host-mode start/submit, protocol description, round diagnosis, H1 computation, evaluation, and offline verification. Although assess_claim, assess_claims_batch, and start_host_assessment all concern assessment, their scopes and execution models are explicitly described, so misselection is unlikely.
All names use consistent snake_case with a verb-leading pattern such as assess_claim, submit_host_round, describe_protocol, evaluate_run, and verify_run. The specialized compute_zigzag_h1 still follows the same convention.
Nine tools is well scoped for a specialized assessment pipeline. Each tool represents a meaningful operation or workflow stage, with no obvious filler tools.
The surface covers the core lifecycle: protocol description, single and batch assessment, host-mode assessment, diagnosis, H1 computation, evaluation, and verification. A minor gap is the lack of an explicit host-session recovery or status-inspection tool, though normal forward flow is complete.