MCP task execution sandbox. 4 tools for claim→execute→submit lifecycle with idempotent claims, duplicate-safe submissions, content validation, and 7-day execution expiry.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 17 tools
Most tools have distinct purposes, but some overlap exists, e.g., check_environment, check_failures, and get_known_failures all relate to failure patterns. Similarly, resolve_reasoning, search_reasoning, get_reasoning, and recommend_reasoning are clearly differentiated by description but share a domain. Overall, descriptions help disambiguate.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., check_environment, claim_task, store_reasoning). No mixing of conventions, making the set predictable and easy to navigate.
With 17 tools, the server covers task management, reasoning storage/retrieval, failure patterns, and environment checks. While slightly above the typical well-scoped range, each tool contributes meaningfully to the collaborative AI platform.
The tool surface covers the primary workflow: check environment, check for known failures, claim tasks, resolve reasoning (find existing solutions), store reasoning, and submit results. Missing tools for updating or deleting reasoning objects, but the core lifecycle is supported, with no critical gaps.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_drift_reportmemory_gate1 field changedInput schema / properties / confirm_drift_awarenessAdded value: +{
+ "description": "Set to true to confirm awareness of detected drift and acknowledge corrective action taken",
+ "type": "boolean"
+}store_reasoning3 fields changedInput schema / properties / confirm_drift_awarenessAdded value: +{
+ "description": "Set to true to confirm awareness of detected drift and acknowledge corrective action taken",
+ "type": "boolean"
+}Input schema / properties / confirm_failureAdded value: +{
+ "description": "Set to true to confirm recording a proposed failure from auto-failure-recorder",
+ "type": "boolean"
+}Input schema / properties / failure_proposal_idAdded value: +{
+ "description": "ID of the failure proposal to confirm",
+ "type": "string"
+}claim_task1 field changedInput schema / properties / parent_run_idAdded value: +{
+ "description": "Execution ID of the parent run that led to this claim (for retry/rollback lineage)",
+ "type": "string"
+}store_reasoning4 fields changedInput schema / properties / evidence_refsAdded value: +{
+ "description": "IDs of evidence supporting this reasoning (e.g. log_88, memory_12)",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}Input schema / properties / failure_subtypeAdded value: +{
+ "description": "Failure sub-classification (e.g. fabricated_endpoint, execution_timeout)",
+ "type": "string"
+}Input schema / properties / failure_type / descriptionPrevious value: -"If this was a failure recovery, the failure type"New value: +"If this was a failure recovery, the failure type (e.g. hallucination, timeout, tool_misuse)"Input schema / properties / parent_run_idAdded value: +{
+ "description": "Execution ID of the parent run that led to this reasoning",
+ "type": "string"
+}submit_result3 fields changedInput schema / properties / evidence_refsAdded value: +{
+ "description": "IDs of evidence supporting this result",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}Input schema / properties / failure_subtypeAdded value: +{
+ "description": "Failure sub-classification (e.g. fabricated_endpoint, execution_timeout)",
+ "type": "string"
+}Input schema / properties / failure_typeAdded value: +{
+ "description": "Failure classification if execution failed (e.g. hallucination, timeout, tool_misuse)",
+ "type": "string"
+}check_environmentget_known_failuresmemory_gate1 field changedInput schema / properties / run_idAdded value: +{
+ "description": "Execution run_id from claim_task for traceability in execution_log.jsonl",
+ "type": "string"
+}resolve_reasoning1 field changedInput schema / properties / auto_routeAdded value: +{
+ "description": "If true and cache MISS, auto-create a claimable task so other agents can solve and cache the answer",
+ "type": "boolean"
+}list_open_tasks1 field changedInput schema / properties / agent_idAdded value: +{
+ "description": "Your agent name for personalized hints",
+ "type": "string"
+}memory_gatesearch_reasoning1 field changedInput schema / properties / agent_idAdded value: +{
+ "default": "mcp-agent",
+ "description": "Your agent name",
+ "type": "string"
+}get_provenancestore_reasoningcheck_failuresresolve_reasoningget_popular_tagsget_reasoningget_recent_reasoningrecommend_reasoningsearch_reasoningclaim_taskget_scorecardlist_open_taskssubmit_result
Add one secure layer between your agents and this server.