Headron MCP
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.
Start with port on the file you will edit: its route, gates, lessons and next commands. failures and successes take a file or an error text, never the whole ledger. The headron tool takes any other read-only command's argv; the exit code is the verdict.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| headronA | Run a read-only Headron CLI command as argv when no dedicated tool fits; verbs: commands, check, proof, invariants, doctor, index, learn, process, index-search, find, do, pick, decide, decide-engine, pipeline, judge, revise, propose, links, model, intake, shell, delegate, handoff, cadence, schedtargets, mind, sweep, role, resume, steps, failures, successes, md, landed, brainstorm, inspect, data, task, port, why, gate, route, compile, plan. Programs: mind --micro list. ["commands", "--json"] lists arguments; exit code is the verdict. |
| portA | START HERE before editing a file: its route, tier, the gates to run, the lessons that apply, and the next commands. Successful structured results include the command record and exit code. |
| routeA | Explain how a file path resolves to a language pack: returns the rule, evidence, guide, manifest and precedence. Use port for the full pre-edit brief; mind_route selects an agent instead. Successful structured results include the command record and exit code. |
| gateA | Show the command and state for a file's named verification gate; it does not execute the command. Use steps for an ordered work plan. Successful structured results include the command record and exit code. |
| stepsA | Build an ordered work plan for one file, including its route and checks; no steps are executed. Tier, change class and runtime shape the plan. Use mind_plan for change classification and isolation guidance. Successful structured results include the command record and exit code. |
| failuresA | Mistakes agents made with a file ( |
| successesA | Look up recorded practices that address recurring failures, including when to use them, evidence and proving instruments. Scope by file or task with |
| proofB | Deterministic scope of a change to one file: its change class, planned gates and tools. Measured verification ( |
| mind_classifyA | Classify a set of changed files by category and risk. Use proof for a single file's planned gates; this does not run verification. |
| mind_planA | Classify changed files and return Mind's planned gates and isolation needs. Use steps for an ordered file-specific work plan; neither runs checks. |
| mind_routeA | Select an agent and model tier for classified changes using capabilities and policy. Use route to explain a file's language pack; this does not authorize or execute an action. |
| mind_healthA | Show Mind API health telemetry, cache statistics, and system status. |
| mind_receiptsA | Retrieve verification receipts and their validity and verdicts. Locally this reads the last verification receipt, if present; a configured hosted service supplies its own results. Validity does not rerun checks. Use proof to plan verification. |
| mind_searchA | Search this repository's code index for a symbol, path or phrase; returns ranked file hits. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| plan-change | the ordered steps that prove a change to one file, for this runtime |
| review-diff | check a pasted diff against the gates its change class requires |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| version | atlas.yaml/version |
| identity | atlas.yaml/identity |
| default_flow | atlas.yaml/default_flow |
| hard_invariants | atlas.yaml/hard_invariants |
| forbidden_calls | atlas.yaml/forbidden_calls |
| absent_input_owners | atlas.yaml/absent_input_owners |
| host_shapes | atlas.yaml/host_shapes |
| enforcement | atlas.yaml/enforcement |
| instrument_roster | atlas.yaml/instrument_roster |
| front_end | atlas.yaml/front_end |
| instruments | atlas.yaml/instruments |
| code_shape | atlas.yaml/code_shape |
| example_runners | atlas.yaml/example_runners |
| external_versions | atlas.yaml/external_versions |
| version_sites | atlas.yaml/version_sites |
| generated_files | atlas.yaml/generated_files |
| state_budgets | atlas.yaml/state_budgets |
| markdown_policy | atlas.yaml/markdown_policy |
| stack_tiers | atlas.yaml/stack_tiers |
| prompt_policy | atlas.yaml/prompt_policy |
| brainstorm | atlas.yaml/brainstorm |
| port | atlas.yaml/port |
| artifact_routes | atlas.yaml/artifact_routes |
| routing_policy | atlas.yaml/routing_policy |
| model_routes | atlas.yaml/model_routes |
| context_policy | atlas.yaml/context_policy |
| verification_policy | atlas.yaml/verification_policy |
| decision_tables | atlas.yaml/decision_tables |
| build_order | atlas.yaml/build_order |
| build_order_rule | atlas.yaml/build_order_rule |
| task_profiles | atlas.yaml/task_profiles |
| data_classes | atlas.yaml/data_classes |
| artifact_edges | atlas.yaml/artifact_edges |
| knowledge_layers | atlas.yaml/knowledge_layers |
| retrieval_policy | atlas.yaml/retrieval_policy |
| asymmetries | atlas.yaml/asymmetries |
| parser_discipline | atlas.yaml/parser_discipline |
| governance_tiers | atlas.yaml/governance_tiers |
| agent_failure_modes | atlas.yaml/agent_failure_modes |
| success_kinds | atlas.yaml/success_kinds |
| not_a_success | atlas.yaml/not_a_success |
| agent_success_patterns | atlas.yaml/agent_success_patterns |
| staleness_discipline | atlas.yaml/staleness_discipline |
| developer_baseline | atlas.yaml/developer_baseline |
| tool_claims | atlas.yaml/tool_claims |
| linguist_names | atlas.yaml/linguist_names |
| process_conditions | atlas.yaml/process_conditions |
| adaptive_recovery | atlas.yaml/adaptive_recovery |
| decomposition_policy | atlas.yaml/decomposition_policy |
| project_manifests | atlas.yaml/project_manifests |
| runtime_entry | atlas.yaml/runtime_entry |
| seats | atlas.yaml/seats |
| native_agent_tools | atlas.yaml/native_agent_tools |
| first_sweep | atlas.yaml/first_sweep |
| topologies | atlas.yaml/topologies |
| drift_review | atlas.yaml/drift_review |
| glance | atlas.yaml/glance |
| intents | atlas.yaml/intents |
| chat | atlas.yaml/chat |
| language_selection | atlas.yaml/language_selection |
| pack_actions | atlas.yaml/pack_actions |
| process_steps | atlas.yaml/process_steps |
| processes | atlas.yaml/processes |
| tool_profiles | atlas.yaml/tool_profiles |
| language_mechanisms | atlas.yaml/language_mechanisms |
| directory_scopes | atlas.yaml/directory_scopes |
| agent_policy | atlas.yaml/agent_policy |
| gate_alias_groups | atlas.yaml/gate_alias_groups |
| gate_tools | atlas.yaml/gate_tools |
| risk_modifiers | atlas.yaml/risk_modifiers |
| authority_classes | atlas.yaml/authority_classes |
| worktree_policy | atlas.yaml/worktree_policy |
| branch_policy | atlas.yaml/branch_policy |
| benchmark_floors | atlas.yaml/benchmark_floors |
| agent_roles | atlas.yaml/agent_roles |
| decision_evidence_backlog | atlas.yaml/decision_evidence_backlog |
| cadence | atlas.yaml/cadence |
| delegation_contract | atlas.yaml/delegation_contract |
| declared_inputs | atlas.yaml/declared_inputs |
| public_surface | atlas.yaml/public_surface |
| install_commands | atlas.yaml/install_commands |
| companions | atlas.yaml/companions |
| pointers | atlas.yaml/pointers |
| orphan_exemptions | atlas.yaml/orphan_exemptions |
| issue_route_terms | atlas.yaml/issue_route_terms |
| issue_routes | atlas.yaml/issue_routes |
| runtime_roles | atlas.yaml/runtime_roles |
TDQS
Scored across 14 tools
Port, steps, proof, gate, route, and the headron catch-all all operate on pre-edit planning/verification for a file, and their descriptions differentiate by nuance rather than clearly separate resource/action boundaries. The headron tool explicitly duplicates many dedicated verbs (proof, steps, failures, successes, port, gate, route, plan), so an agent could easily choose the wrong entry point.
All names are lowercase snake_case and readable, but there is no consistent verb_noun convention: some are bare nouns (gate, steps, port, route, proof) while others use a mind_ prefix (mind_search, mind_receipts, mind_classify). The mix of prefixed and unprefixed families makes naming only partially predictable.
Fourteen tools is within a reasonable range for a repo-analysis and verification server. However, several overlap-heavy planning tools (port, steps, proof, gate, route) reduce the sense that every tool earns its place, and the catch-all headron inflates the effective surface.
For a read-only change-planning and verification domain, the surface covers search, routing, gates, plans, receipts, failure/success lookup, and health telemetry. Missing direct execution or recording capabilities appear intentional or are handled through the CLI fallback, leaving only minor gaps.