// MCP TOOL REFERENCE

ELIXIUM AI TOOLS

43 tools from the Elixium Ai MCP Server, categorised by risk level.

// ALL 43 ELIXIUM AI TOOLS

READ 27 tools

Read draft_hypothesis Generate an AI-drafted hypothesis for the given story and submit it as a pending proposal. The backend call... Read draft_test_plan Return a starter test plan scaffold seeded from the story Read endorse_proposal Endorse a pending field proposal. Updates the underlying story field with the proposal Read estimate_cost Generate AI-assisted infrastructure cost estimate for a story. Uses live cloud pricing data when available. Read get_board_context Get a snapshot of the workspace Read get_epic_cost_rollup Get aggregated infrastructure cost for all stories in an epic. Shows total monthly cost, category breakdown... Read get_feature_config Get the feature configuration for this board/workspace. Returns enabled features, team profile, and smart d... Read get_infrastructure_profile Get the workspace infrastructure profile. Returns cloud provider, regions, compliance frameworks, existing ... Read get_iteration_context Get the current iteration context (Current + Backlog) for AI planning Read get_stakeholders Derive the set of trust audiences this story needs to earn trust with. Returns an array of {audience, reaso... Read get_story Get full details for a single story by UUID. Returns all fields including description, acceptance criteria,... Read get_test_plan Retrieve and display the full TDD test plan for a story. Shows the plan text, workflow stage, approval stat... Read get_trust_leakage Return the tenant Read list_boards List all boards in the workspace. Returns id, name, slug, and story count for each board. Marks the current... Read list_decisions List recent team decisions. Filter by category, tag, or date. Use this to check what the team has decided r... Read list_epics List epics for the current board Read list_knowledge_sources List all knowledge sources indexed in the RAG knowledge base, grouped by source type. Read list_objectives List objectives for the current workspace Read list_stories List stories on the Elixium board. Returns compact summaries (id, title, lane, points, owners, epic, state)... Read prepare_implementation Fetch all context for a story and format an implementation brief Read prioritize_epic AI-powered dependency analysis and story prioritization for an epic. Analyzes stories, proposes optimal exe... Read propose_field_draft Submit an AI-drafted value for a Learning Loop field as a pending proposal. The draft does NOT change the s... Read propose_test_plan Submit a test plan for human review. Sets workflow_stage to tests_proposed. Implementation is BLOCKED until... Read record_decision Record a team decision, meeting outcome, or architectural choice. These are shared across all team members Read record_learning Record a learning outcome for a completed story (sets the story Read search_decisions Full-text search across all team decisions. Use this when looking for decisions related to a specific topic... Read search_knowledge Semantic search across team knowledge base (documents, wikis, runbooks, etc). Returns relevant chunks with ...

WRITE 12 tools

Write add_blocker Declare a structural dependency: storyId is blocked by blockerStoryId, for the given reason. Adds one entry... Write approve_tests Approve a proposed test plan so implementation can proceed. Transitions workflow from tests_proposed to tes... Write create_board Create a new board in the workspace. Auto-generates slug from name if not provided. Max 3 active boards per... Write create_epic Create an epic for the active board. Epics group related stories around an outcome hypothesis. Before creat... Write create_hypothesis Create a new assumption/hypothesis in the Icebox for validation. Before creating, ensure you are grounded —... Write create_story Create a story on the active board. New stories enter the Backlog lane and are attributed to the user bound... Write reject_proposal Reject a pending field proposal with a required reason. Story field is unchanged; reason is captured for ag... Write select_board Switch the active board context. All subsequent tool calls (list_stories, create_story, list_epics, etc.) w... Write submit_for_review Submit implementation for human review. Only works if tests are approved. Sets state to finished. Write update_epic Update an epic Write update_story Update fields on an existing story. Accepts Learning Loop fields (hypothesis, confidence_score, hidden_unkn... Write update_three_amigos_check Attest engineering/design/product readiness for the story; each role is its own write target with its own a...

DESTRUCTIVE 2 tools

Destructive delete_proposal Discard a proposal you created. If the proposal was endorsed and mutated a story field, the field is revert... Destructive remove_blocker Remove a previously-declared dependency: drop blockerStoryId from storyId

EXECUTE 2 tools

Execute review_pr Run AI review on a story Execute start_story Start TDD workflow for a story. By default creates a feature branch. Set trunkBased=true to work directly o...

// RUNNING THIS SERVER

The managed route: connect Elixium Ai through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @elixium.ai/mcp-server

// FAQ

How many tools does the Elixium Ai MCP server have? +

The Elixium Ai MCP server exposes 43 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Elixium Ai tools? +

Route the Elixium Ai server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Elixium Ai tools fall into? +

Elixium Ai tools are categorised as Read (27), Write (12), Destructive (2), Execute (2). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.