keystone-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KEYSTONE_CONFIG | No | Path to the configuration YAML file (default: .keystone/context.yaml) | .keystone/context.yaml |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| keystone_get_contextC | Full envelope (rules + reasoning + skills + commands) for a topic. |
| keystone_list_topicsA | List configured topics. Pass |
| keystone_harness_bootstrapA | Create Idempotent — existing subdirs and files are reported in Pass |
| keystone_new_guideA | Scaffold a new guide markdown file under
|
| keystone_new_sensorA | Scaffold a new sensor + its matching implementation. Sensors are blocking rules.
|
| keystone_new_scriptA | Scaffold a shell script under Use this to drop a script body without a sensor wrapper, or to
refresh an existing script (with |
| keystone_new_promptA | Scaffold a prompt markdown under Used by inferential sensors — the agent reads the prompt and
performs the reasoning task it describes. Most projects scaffold
inferential sensors via |
| keystone_new_skillA | Scaffold Skills are the FastMCP-native primitive for agent-discoverable
procedural how-to. Each subdirectory containing a Manager-authored skills are named |
| keystone_new_actionA | Scaffold a new action markdown under Actions are short, focused operations the agent walks during a
task — |
| keystone_new_playbookB | Scaffold a new playbook markdown under Playbooks orchestrate multiple actions into a higher-level flow
with explicit phase gates: |
| keystone_new_corpusA | Scaffold a new corpus markdown under Corpus entries are reasoning / background context — domain
notes, architecture decisions, idioms. Not constraints (those
go in |
| keystone_new_adapterB | Scaffold a per-agent adapter directory under |
| keystone_target_addA | Install the agent's menu file(s) at the project root. Menu files (CLAUDE.md, AGENTS.md, etc.) point the agent at
|
| keystone_apply_patchesA | Apply every pending shipped patch to the project harness. Patches are forward-only. Files modified by the user since the
previous shipped version are skipped and reported as
conflicts; the user resolves them by hand. Today no patches
ship — the call reports an empty |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| keystone_bootstrap | Seed the bootstrap workflow: analyze the codebase and fill the project's state ledgers under `.keystone/harness/corpus/state/`. |
| keystone_task | Seed the task workflow on a unit of work. Walks spec → orient → implement → check-drift → verify → review. Pause for explicit user acceptance between phases. |
| keystone_audit | Seed the dual-flywheel audit: learning + pruning. |
| keystone_learn | Seed the learn workflow: capture a finding into learning/inbox/. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| context_list_resource | |
| harness_status_resource | |
| harness_options_resource | |
| harness_verify_resource | Cascade-engine resolution report for the current harness (Phase 20). Surfaces unreachable items, canonical violations, required gaps, and non-canonical conflicts. Read-only — no side effects. |
| harness_doctor_resource | Full audit report — cascade verify + path conformance + ambient-load budget proxy. Read-only. |
| harness_patch_pending_resource | Pending shipped patches against the current harness (Phase 21). Lists files that would be written if the consumer ran the patch playbook, plus files skipped because the consumer has modified them since the previous shipped version. |
| harness_budget_resource | Ambient-load budget report for the project harness (Phase 27). Per-port totals, top hot files, approximate-token counts via a deterministic word-count proxy, and (when the cascade marks items unreachable) a `cascade_excluded` block. |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tacoda/keystone-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server