Akashic corpus + Laya routing. Anonymous read; free signup in-band.
The last two health checks of this connector failed. 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 24 tools
Most tools have clearly distinct resource/action targets across corpus, registration, LLM keys, CI/CD, and monitoring. The main overlaps are corpus_item vs read_corpus_item, and search_corpus vs corpus_route can be confused by an agent choosing discovery vs routing behavior. These are minor but real ambiguities in an otherwise well-separated tool set.
The set is consistently snake_case and mostly follows verb_noun patterns such as register_agent, search_corpus, list_llm_keys, and generate_cicd_workflow. A few tools deviate with noun-first corpus_* names or mixed discovery verbs like get/read/fetch/check, but the convention remains readable and predictable overall.
At 24 tools this is on the heavy side for a single MCP server, even accounting for the broad platform scope spanning corpus, accounts, agents, BYOK keys, CI/CD, and monitoring. The surface is not wildly excessive, but consolidation could reduce cognitive load for agents.
The surface covers the core lifecycle well: corpus discovery/routing/read/outcome, account/agent/org registration, LLM BYOK key management, CI/CD generation, deployment planning, HITL visibility, and research tracing. Minor gaps remain around HITL approval actions, account/agent management beyond registration, and interaction creation for the research chain, but agents can largely work around them.
Trigger analysis on a repository. Returns the analysis run ID and status.
Inputs: repo_path (required), entity_id, interaction_id. Returns: result
List heartbeat monitor status (8 condition-based monitors) or trigger a manual heartbeat check cycle. Monitors watch for PR merges, deploy failures, test failures, dependency drift, doc drift, security advisories, stale branches, and failing suites.
Inputs: entity_id, trigger_check. Returns: result
Bind a registered agent to a user or org account so it acts on their behalf (acted_for grant). Requires a signature from the agent over claim:{agent_id}:{entity_id} — the agent consents, and the account consents. The agent keeps its own identity.
Inputs: agent_id (required), signature (required), claimant_entity_id (required), scopes, +1 more. Returns: result
List the corpus domain lanes (261 domains of repos, docs, code examples, issues) with item counts — the discovery index for corpus_route and corpus_item.
Inputs: product. Returns: result
Read one corpus item's full record — evidence, license, quality, tags. Items above your visibility class return an account_required pointer.
Inputs: item_id (required). Returns: result
Report whether a cited corpus item helped — feeds Laya's routing flywheel so the corpus improves with use. Anonymous reports count at reduced weight.
Inputs: domain (required), item_id (required), success (required), note. Returns: result
Route a task through Laya to the best corpus item — returns the decision kind, picked item, score, and citations. Items above your visibility class return an account_required pointer.
Inputs: task (required), domain. Returns: result
Draft a deployment plan from a ticket or repository. Returns the drafted plan with stages.
Inputs: source_repo (required), workspace_id (required), environment, cicd_provider, +1 more. Returns: result
Fetch pending HITL approval items with RBAC context (agent identity, caller role, required permission, and approval eligibility). Use this to check what needs human approval before proceeding.
Inputs: status, category. Returns: result
Generate a CI/CD workflow (GitHub Actions, Bitbucket Pipelines, GitLab CI, or Tekton) with build, test, deploy, and callback stages. Returns YAML, filename, stages, and per-field research basis.
Inputs: provider (required), repo_path (required), tier, test_command, +3 more. Returns: result
Returns the canonical onboarding flow for every caller class — anonymous, human signup, autonomous agent, agent binding, and org creation. Call this first if you're unsure how to proceed.
Inputs: no named parameters. Returns: result
Discover the ColossalCapital platform's public capabilities — fetches llms.txt. No account required. Use this first to learn what tools and APIs are available.
Inputs: no named parameters. Returns: result
Fetch the interaction chain for a given interaction ID, showing all artifacts (heartbeat, analysis, ticket, agent, PR, deployment) in the closed loop. If no interaction_id is provided, lists all known interaction IDs.
Inputs: interaction_id. Returns: result
List which LLM providers have stored keys (never the keys themselves). Use to check BYOK configuration status.
Inputs: no named parameters. Returns: result
List LLM providers you can bring keys for (BYOK). The platform runs on your keys — inference cost is yours, ours is the routing.
Inputs: no named parameters. Returns: result
Read a public Akashic corpus item in full. Items above the public class return an account_required pointer.
Inputs: entry_id (required). Returns: result
Register a free ColossalCapital account for a human user. Creates the identity immediately (free tier, no billing) and returns a link_token to claim the Idio login later. Call this when a tool returns account_required, or when a user asks to sign up.
Inputs: name (required), email (required), use_case, captcha_token, +1 more. Returns: result
Register an autonomous agent as a first-class account (entity_type=agent). The Ed25519 public key is the only credential — no password. Gets a prepaid wallet for metered tools. Can later be bound to a user via claim_agent without losing its identity.
Inputs: name (required), ed25519_pubkey (required), intended_use, operator_contact. Returns: result
Register an organization account. Employees who signed up individually keep their accounts — org membership is added to them, never recreated. Returns the org's API key.
Inputs: name (required), contact_email (required), industry, contact_name. Returns: result
Remove a stored BYOK provider key from the vault.
Inputs: provider (required), scope. Returns: result
Search the Akashic corpus — the platform's knowledge base of tools, stack layers, design patterns, and exemplars. Public entries only; no account required. Register via register_account or register_agent for the full corpus.
Inputs: limit, query, technology, stack_layer. Returns: result
Search for relevant skillfiles by query or persona. Skillfiles are the behavioral guidance layer for agents — they define how agents should write tests, create PRs, lint code, review, and generate CI/CD workflows.
Inputs: query, persona. Returns: result
Store a BYOK LLM provider key in the encrypted vault. Validated against the provider before storing. scope='org' stores an org-wide key (admin-only). Requires an account — call register_account or authenticate first.
Inputs: api_key (required), provider (required), scope, validate. Returns: result
Test an LLM provider key against the provider without storing it. Use before set_llm_key if you want to check validity first.
Inputs: api_key (required), provider (required). Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
A public relay where AI instances read traces left by others and may leave one. No auth.
Public chat and shared memory for AI agents. Open reads, free write keys. MCP + A2A + WebSocket.
Keyless, read-only Lazyweb discovery for agents evaluating fit or researching public evidence.
Provider-neutral commons where AI agents register and exchange ed25519-signed messages.
Add one secure layer between your agents and this server.