deep-agentic-core-mcp
OfficialServer 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 |
|---|---|
| core.healthA | Return rich server diagnostics: adapter availability, loaded tools/resources/prompts, and recent successful calls. |
| core.versionA | Return the current server package version. |
| core.verifyA | Check connectivity to agenticlens, agentic-chaos, agentic-sidecar, and ai-operations-spec, and report readiness. |
| core.session_stateA | Inspect the artifacts and call history accumulated in a session. |
| lens.analyze_workflowC | Analyze an AgenticLens-compatible workflow artifact. |
| lens.report_summaryA | Render a Markdown workflow report and recommendation summary. 'artifact' may be omitted to reuse the session's stored workflow. |
| lens.compare_runsA | Compare baseline and candidate trace runs for regressions. 'baseline'/'candidate' may be omitted to reuse the session's stored runs. |
| lens.slo_summaryB | Apply release-gate style SLO thresholds to an evaluation report. |
| lens.audit_reportC | Return case-by-case evaluation detail for an audit trail. |
| chaos.list_faultsA | List the supported fault types for chaos experiments. |
| chaos.run_experimentA | Run a workspace-sandboxed target script under selected chaos faults and report the resulting events. |
| sidecar.statusA | Report whether agentic-sidecar is importable and whether its decision runtime is actually ready yet. |
| sidecar.module_inventoryA | List the current scaffolded modules, framework adapters, and integration placeholders present in agentic-sidecar. |
| spec.validate_artifactB | Validate a workflow or run artifact against the AI Operations v0.4 draft. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| lens.workflow_summary | Summarize an analyzed workflow for a human operator. |
| lens.compare_summary | Summarize a baseline-vs-candidate run comparison for a release decision. |
| chaos.experiment_brief | Explain the intent and expected impact of a chaos run. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Sample workflow artifact | |
| Chaos fault catalog |
TDQS
Scored across 14 tools
Each tool is grouped under a clear domain prefix and has a distinct action, but core.health/core.verify both touch readiness and lens.report_summary/lens.slo_summary/lens.audit_report are all report-like. The descriptions clarify the boundaries well, leaving only minor potential for confusion.
Names consistently use lowercase dotted namespaces with snake_case and mostly follow a verb_noun pattern (analyze_workflow, compare_runs, run_experiment). A few noun-only names (core.health, core.version, sidecar.status) break the verb-first pattern, but the convention is still predictable.
Fourteen tools is well within the ideal range and each tool serves a distinct purpose across five focused domains. No tool feels redundant or gratuitous for a server covering core diagnostics, lens analysis, chaos, sidecar, and spec validation.
The tool set covers the advertised surface well: health/readiness, workflow analysis, run comparison, SLO evaluation, audit, chaos experiments, sidecar inspection, and artifact validation. Minor gaps exist around creating/modifying/storing artifacts, but they may be outside the server's intended scope and do not create obvious dead ends.