Skip to main content
Glama
Mustafa-Ali-Ertugrul

AllBrain MCP

by Mustafa-Ali-Ertugrul
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

AllBrain Agent Runtime

One brain. Many agents. One shared memory.

CI PyPI Downloads Python License Ruff

AllBrain Agent Runtime banner

demo

Without AllBrain vs with AllBrain

Scenario

Without AllBrain

With AllBrain

Agent A saves a plan

Written to local chat history, immediately lost when session ends

Appended to shared event store via save_event()

Agent B starts the same project

Fresh context — no knowledge of Agent A's work

resume_project() returns full event history

Two agents write conflicting changes

Silent overwrite, no one knows

detect_conflicts() surfaces both versions

Handoff between agents

Manual copy-paste of context

list_events() with agent filter shows handoff trail

Debugging state drift

"It worked in my session"

Deterministic replay from raw events, exactly reproducible

Related MCP server: Enhanced Sequential Thinking MCP Server

The problem

Your AI coding agents don't talk to each other. Agent A saves a plan, Agent B starts fresh, Agent C has no idea what happened. Each agent works in isolation, repeating mistakes and missing context.

AllBrain gives every agent a shared workbench. Each tool call is recorded in an append-only event store. When the next agent arrives, it sees everything that happened before — events, sessions, conflicts, decisions — and picks up cleanly.

What AllBrain gives you

  • Shared memory — save_event, list_events, resume_project across any MCP client

  • Agent attribution — every event is tagged with the agent that wrote it

  • Conflict detection — automatic surface of conflicting state updates

  • Decision pipelines — counterfactual reasoning, scenario planning, foresight

  • Deterministic replay — rebuild project state from raw events

  • 53 tools in full profile across 18 domain modules (start with 3, enable more as needed)

30-second demo

# Agent A: save a plan
uv run allbrain start --project . --agent agent-a
# In Agent A's client, call:
#   save_event(type="task_planned", payload={"task": "implement auth"})
# Agent B: see what Agent A did
uv run allbrain start --project . --agent agent-b
# In Agent B's client, call:
#   list_events()
#   resume_project()

See examples/two_agent_sqlite_pilot.py for a full two-agent workflow with conflict detection and replay verification.

Install for one client

The PyPI distribution is allbrain-agent-runtime. The canonical CLI command is allbrain; allbrain-mcp and allbrain-agent-runtime remain compatibility aliases for existing installations and scripts.

uvx allbrain-agent-runtime install --codex

This configures Codex to start AllBrain automatically. Replace --codex with the client name:

Client

Flag

Codex

--codex

Claude Code

--claude

OpenCode

--opencode

Cursor

--cursor

VS Code

--vscode

Zed

--zed

Gemini CLI

--gemini

Kiro

--kiro

Windsurf

--windsurf

Antigravity

--antigravity

Claude Desktop

--claude-desktop

Use --all to configure every supported client at once.

Verify it works

uvx allbrain-agent-runtime install --codex --verify

The --verify flag starts the server, saves a test event, reads it back, and confirms shared memory is working.

Tool profiles

Start with --tool-profile minimal (3 tools) and expand when needed:

Profile

Tools

Use when

minimal

save_event, list_events, resume_project

Getting started

memory

minimal + retrieve_memory

Need recall

collaboration

memory + task/conflict/resolution tools

Multi-agent handoff

reasoning

memory + decision pipeline tools

Planning and analysis

core

save_event, list_events, retrieve_memory, git_info, create_task, get_task_graph, orchestrate_project, run_decision_pipeline, create_snapshot, resume_project, get_context_pack

Essential workflow + context pack

full

53 tools

Complete surface across all 18 tool modules

uv run allbrain start --project . --agent my-agent --tool-profile memory

Glama MCP Portal

Glama MCP evaluates this server with the balanced core tool profile (--tool-profile core in glama.json). Its 11 public tools cover shared memory, task orchestration, snapshots, Git context, and decision workflows without exposing the entire development surface.

For local development or to access all capabilities, use the full profile:

uv run allbrain start --project . --agent claude-code --tool-profile full

Alternatively, standard client configurations like .mcp.json (which default to full) can be used.

From source

git clone https://github.com/Mustafa-Ali-Ertugrul/allbrain-mcp.git
cd allbrain-mcp
uv sync
./scripts/install-mcp.sh --all --isolate --verify

Or run the guided onboarding wizard:

uv run allbrain onboard

It walks you through client selection, install, verification, and your first event step by step.

See the full setup guide for manual config, troubleshooting, and shared-vs-isolated databases.

First memory save

Once AllBrain is installed and the client is restarted, call:

save_event(type="task_started", payload={"task": "implement auth", "agent": "codex"})

Then verify it was recorded:

list_events()

Switch to another client, call list_events() again — the same event appears.

Tool count and supported clients

Note: Glama evaluates the balanced 11-tool core profile. The full profile remains available for local development.

  • 53 tools in the full MCP profile across 18 server tool implementation modules (src/allbrain/server/tools/)

  • Default profile (full) registers all tools

  • minimal profile: 3 tools (save_event, list_events, resume_project)

  • core profile: 11 tools (essential workflow + reasoning + context pack)

What's New in v1.1.0

Security hardening (threat-model remediation)

  • Fail-closed sanitization (§B1): Depth-limit bypass closed; configurable max depth and payload size cap.

  • gitbrain RCE sandbox (§D): No-shell argv, hard env isolation, and dangerous git config overrides.

  • SQLite permissions (§E1): Restrictive file/dir modes and umask hardening (Windows best-effort documented).

  • Memory poisoning defense (§1): Event-sourced quarantine, default exclusion from context, untrusted event boundaries, promote_event / review_quarantined.

  • Safe install (§C1): .mcp.json backup + merge + confirm/--force + integrity hash.

  • Windows path hardening (§C2): Case-insensitive normcase + realpath containment checks.

  • Event hash-chain (§A2): Lightweight tamper-evidence via chained payload hashes.

Runtime changes

  • Full tool surface: 53 tools (promote_event, review_quarantined added)

  • list_events default limit raised to 1000

  • CI matrix: Python 3.12 & 3.13, coverage gate 85%

What's New in v1.0.0

1. 6 Bounded Contexts & 73 Domain Modules Migration

  • Modular Namespace: All 73 domain packages have been reorganized into the canonical allbrain.domains.* namespace across 6 bounded contexts: reasoning, analysis, learning, governance, memory, and collaboration.

  • Backward Compatibility Shims: Root imports (allbrain.<module>) remain functional with DeprecationWarning and are slated for removal in v2.0.0.

2. High-Performance Benchmarks & FastMCP Engine

  • Cold Startup: $\le 0.11$s server initialization.

  • Throughput: 277–371+ eps across varying payload sizes on local SQLite WAL.

  • Snapshot Generation: 0.091s for 10,000 events.

  • Memory Footprint: ~150 MB RSS peak under concurrent load.

3. Production Security & Verification

  • Secret Redaction: Multi-layer masking for 13+ secret formats and Pydantic validation error sanitization.

  • Input Validation: Strict Pydantic models with null-byte rejection and prompt injection filtering across MCP tools.

  • Filesystem Sandbox: ALLBRAIN_ALLOWED_PROJECT_ROOTS path traversal isolation.

  • Dual-Window Rate Limiting: Process-local thread-safe rate limiter (1,000 RPS burst, 100,000 RPM rolling).

Data lifecycle and security

AllBrain stores events, sessions, and audit logs in local SQLite. Data never leaves your machine. Credential-like values are redacted before storage.

Advanced docs

Status

  • 3,110 passed tests, 5 skipped tests (100% green)

  • 53 tools in full profile

  • stdio FastMCP handshake verified

  • Python 3.12 & 3.13 (CI matrix)

  • Coverage: 86.54% (enforced threshold 85%)

Available Tools

5 tools
create_taskA

Create a new task in the event-sourced task graph for multi-agent orchestration.

Use this to add work items before assigning them to agents. For updating an existing task's priority, use change_task_priority instead. This appends a TASK_CREATED event to the append-only SQLite event log with stable UUIDv7 ordering.

Side effects: Creates a TASK_CREATED event in the project's event log. Triggers an automatic snapshot when the event threshold is reached. Does NOT assign the task.

ParametersJSON Schema
NameRequiredDescriptionDefault
goalYesRequired task objective (1-3 sentences recommended). Should describe what needs to be accomplished, not how.
kindNoTask category (default "implementation"). Common values: "implementation", "review", "testing", "research", "design".implementation
task_idNoOptional explicit task ID; if omitted, a stable UUIDv7 is auto-generated.
priorityNoImportance level from 1 (low) to 5 (critical); higher priority tasks are scheduled first by the deterministic scheduler. Default 3.
related_filesNoOptional list of file paths this task touches; helps agents provide relevant context and reduces hallucination risk.

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses side effects: creates TASK_CREATED event, triggers automatic snapshot, does not assign task. Also describes event-sourced nature and ordering.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each serving a distinct purpose: purpose, usage, side effects. No redundant content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists, description covers essential behavioral and usage context for a 5-parameter tool. Side effects and usage boundaries are clear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with detailed parameter descriptions. The tool description does not add parameter-specific information beyond the schema, so baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a new task in an event-sourced task graph for multi-agent orchestration, with specific verb and resource. It distinguishes from sibling change_task_priority.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance: 'Use this to add work items before assigning them to agents' and 'For updating an existing task's priority, use change_task_priority instead'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

git_infoA

Retrieve git repository context, working tree status, or recent changes.

Consolidated tool replacing the previous get_git_context, get_git_status, and get_recent_changes tools. Use info_type to select what subset to return.

"all" returns branch, remote, recent commits, working tree status, and staged/ modified/untracked file lists in a single response. Use this when you need the full picture before making changes.

Side effects: Read-only operation; queries git repository.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMax commits to return (default 100). Work summaries report ``truncated=true`` when more commits exist in the time window.
sinceNoOptional inclusive ISO timestamp for "work_summary".
untilNoOptional exclusive ISO timestamp for "work_summary".
info_typeNoWhat git information to return: - "all": branch, remote, commits, and working tree status (default) - "context": branch name, remote URL, list of recent commits - "status": working tree status with staged/modified/untracked files - "changes": recent commits from the current branch - "work_summary": date-filtered commit/file/line summary across all branchesall

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Explicitly states 'Read-only operation; queries git repository' as side effects. With no annotations, description fully covers behavioral transparency. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise paragraphs front-loaded with purpose, then details on 'all' option, then side effects. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a read-only tool with 4 parameters (none required) and output schema. Describes info_type options, purpose, and side effects. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. Description does not add substantial meaning beyond parameter descriptions in schema, except for mentioning consolidation context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb 'Retrieve' and resource 'git repository context, working tree status, or recent changes'. Explicitly states it's a consolidated tool replacing previous ones, distinguishing its purpose from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States to use 'info_type' to select subset and advises using 'all' when needing full picture before changes. Provides clear context for when to use but does not explicitly mention when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_eventsA

Query and filter recorded events from the append-only event log.

Use this to inspect the history of agent actions and system state changes. Events are ordered by stable UUIDv7 timestamps for consistent replay.

Side effects: Read-only operation; no data is modified.

ParametersJSON Schema
NameRequiredDescriptionDefault
typeNoOptional event type to filter by (e.g., "TASK_CREATED", "TASK_ASSIGNED", "TOOL_CALLED").
limitNoMaximum number of events to return (default 50). Increase for broader history inspection.
session_idNoOptional session ID to filter by (useful for multi-agent debugging and isolation).

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Explicitly declares read-only nature and mentions ordering by UUIDv7 timestamps for consistent replay, providing good behavioral context beyond the absence of annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences front-loaded with the purpose, followed by usage and side effects, with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, usage, ordering, and side effects; with an output schema present, it need not explain return values, making it complete for this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description does not add new meaning to parameters beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries and filters events from an append-only event log, distinguishing it from siblings like save_event or summarize_sessions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It advises using the tool to inspect history of agent actions and system state changes, but does not explicitly state when to avoid it or mention alternatives beyond implicit context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

retrieve_memoryA

Semantic search over stored memories to find similar workflows and patterns.

Use this to discover relevant past work when facing a new task. Returns both similar workflows and common failure patterns that match the query.

Side effects: Reads from the semantic memory store built by build_memory. Use build_memory first to ensure the index is up-to-date.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of events to scan for similarity (default 5000).
queryYesSearch query string describing the problem or goal. Use natural language; the semantic retriever handles embedding.
top_kNoNumber of top results to return (default 5, max 50).

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, description takes full burden. States side effect: 'Reads from the semantic memory store built by build_memory,' clarifying it's a read-only operation and identifying dependency. No mention of auth or rate limits, but the simple read nature reduces concern.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences with no redundant text. Main purpose announced first, followed by usage guidance, side effects, and prerequisite. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given presence of output schema and simple search tool behavior, description adequately covers purpose, usage, and side effects. Does not detail return format but output schema handles that. Lacks mention of pagination or timeouts, but not critical for this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage, so baseline is 3. Description adds context that query uses natural language and embedding is handled, providing some value beyond schema. However, it does not add critical new information for each parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Semantic search over stored memories' with specific verb and resource. Differentiates from sibling tools by focusing on semantic retrieval of similar workflows and patterns, which is distinct from creating tasks or listing events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear usage context: 'Use this to discover relevant past work when facing a new task.' Also gives a prerequisite: 'Use build_memory first to ensure the index is up-to-date.' Does not explicitly state when not to use or name alternatives, but the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

save_eventA

Append an event to the shared event log with optional metadata.

Use this to record agent actions, decisions, and state changes. All events are append-only with stable UUIDv7 ordering, enabling deterministic replay.

Side effects: Creates a new event in the SQLite event log. Triggers an automatic snapshot when the event threshold is reached. This is the primary write operation for the event-sourced architecture.

ParametersJSON Schema
NameRequiredDescriptionDefault
typeYesEvent type identifier (e.g., "TASK_CREATED", "TASK_ASSIGNED", "TOOL_CALLED", "DECISION_MADE").
branchNoOptional branch name (for git-based project tracking).
sourceNoEvent source label (default "agent"). Use "allbrain" for system-generated events, or the agent name for agent actions.agent
payloadYesEvent data as a JSON-serializable dict. Should contain the relevant state or information being recorded.
caused_byNoOptional causal event reference (creates event provenance).
file_pathNoOptional source file path (for code-related events).
task_hintNoOptional task hint string (helps with memory building).
importanceNoOptional importance rating (1-5); higher values may trigger more frequent snapshots.
session_idNoOptional session ID to associate with (for multi-agent tracing).
impact_scoreNoOptional impact score for decision events.

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses side effects: creates event in SQLite, triggers automatic snapshot on threshold. Annotations are absent, so description carries full burden and meets it well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise with four front-loaded sentences. No fluff, every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 10 parameters and output schema, description covers purpose, usage, and side effects. Could mention event type conventions or error handling, but still adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. Description adds no parameter-specific info beyond schema, but overall context is present.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Append an event to the shared event log' with specific verb and resource. It distinguishes from sibling 'list_events' and calls it the primary write operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Guidance is given: 'Use this to record agent actions, decisions, and state changes.' However, it does not explicitly exclude use cases or compare with alternatives like 'build_memory'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 5 tool updatesv1.0.0
    • Removedcreate_snapshot
    • Removedget_task_graph
    • Removedorchestrate_project
    • Removedresume_project
    • Removedrun_decision_pipeline
  2. 7 tool updatesv0.1.6
    • Addedcreate_snapshot
    • Addedcreate_task
    • Addedget_task_graph
    • Addedgit_info
    • Addedorchestrate_project
    • Addedretrieve_memory
    • Addedrun_decision_pipeline
  3. 47 tool updatesv0.1.5
    • Removedadd_task_dependency
    • Removedassign_task
    • Removedbuild_memory
    • Removedchange_task_priority
    • Removedclaim_task
    • Removedcleanup_stale_sessions
    • Removedclose_session
    • Removedcompare_agents
    • Removedcomplete_task
    • Removedcreate_snapshot
    • Removedcreate_task
    • Removeddelete_task
    • Removeddetect_conflicts
    • Removeddetect_contradictions
    • Removeddetect_knowledge_gaps
    • Removedestimate_confidence
    • Removedestimate_information_gain
    • Removedestimate_uncertainty
    • Removedevaluate_plan
    • Removedevaluate_scenarios
    • Removedexplain_decision
    • Removedextract_intents
    • Removedfail_task
    • Removedgenerate_counterfactual
    • Removedgenerate_future_plans
    • Removedgenerate_scenarios
    • Removedget_observability_dashboard
    • Removedget_reliability_status
    • Removedget_system_metrics
    • Removedget_task_graph
    • Removedgit_info
    • Removedhandoff_task
    • Removedidentify_information_needs
    • Removedobserve_world
    • Removedorchestrate_project
    • Removedrank_alternatives
    • Removedrecommend_policy
    • Removedrenew_task_lease
    • Removedresolve_conflicts
    • Removedresume_with_intent
    • Removedretrieve_memory
    • Removedrun_decision_pipeline
    • Removedsimulate_action
    • Removedsummarize_sessions
    • Removedui_view
    • Removedupdate_task
    • Removedworkflow_info
  4. 60 tool updatesv0.1.1
    • Changedadd_task_dependency3 fields changed
      • addedInput schema / properties / depends_on / description
        Added value: +"ID of the prerequisite task (must complete first)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / task_id / description
        Added value: +"ID of the dependent task (the one that must wait)."
    • Changedassign_task4 fields changed
      • addedInput schema / properties / agent_id / description
        Added value: +"Optional explicit agent ID (e.g., \"codex\", \"claude\", \"opencode\").\nIf None, auto-selects the best-fit agent using the DeterministicScheduler."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider when building task state for agent selection\n(default 5000). Increase for large projects with extensive history."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / task_id / description
        Added value: +"ID of the task to assign (must exist in the event log)."
    • Changedbuild_memory2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to index (default 5000). Increase for\nprojects with extensive history, but note this may affect performance."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedchange_task_priority4 fields changed
      • addedInput schema / properties / new / description
        Added value: +"New priority value from 1 (lowest) to 5 (critical)."
      • addedInput schema / properties / old / description
        Added value: +"Previous priority value (optional, for audit trail and debugging)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / task_id / description
        Added value: +"ID of the task to update."
    • Addedclaim_task
    • Addedcleanup_stale_sessions
    • Addedclose_session
    • Changedcompare_agents2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to process (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Addedcomplete_task
    • Changedcreate_snapshot4 fields changed
      • addedInput schema / properties / force / description
        Added value: +"Whether to force creation even if no new events exist since last\nsnapshot (default False)."
      • addedInput schema / properties / include_derived / description
        Added value: +"Whether to include derived/computed state in addition to\nraw events (default False). Increases snapshot size."
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to include (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedcreate_task7 fields changed
      • removedInput schema / properties / agent_id
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / goal / description
        Added value: +"Required task objective (1-3 sentences recommended). Should describe what\nneeds to be accomplished, not how."
      • addedInput schema / properties / kind / description
        Added value: +"Task category (default \"implementation\"). Common values: \"implementation\",\n\"review\", \"testing\", \"research\", \"design\"."
      • addedInput schema / properties / priority / description
        Added value: +"Importance level from 1 (low) to 5 (critical); higher priority tasks are\nscheduled first by the deterministic scheduler. Default 3."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / related_files / description
        Added value: +"Optional list of file paths this task touches; helps agents provide\nrelevant context and reduces hallucination risk."
      • addedInput schema / properties / task_id / description
        Added value: +"Optional explicit task ID; if omitted, a stable UUIDv7 is auto-generated."
    • Addeddelete_task
    • Changeddetect_conflicts3 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to scan (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / threshold / description
        Added value: +"Similarity threshold for conflict detection (default 0.7).\nLower values are more sensitive; 0.7-0.9 is recommended."
    • Changeddetect_contradictions2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to analyze (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changeddetect_knowledge_gaps3 fields changed
      • addedInput schema / properties / decision_id / description
        Added value: +"ID of the decision to analyze for knowledge gaps."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedestimate_confidence3 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider for historical analysis (default 5000)."
      • addedInput schema / properties / plan_id / description
        Added value: +"The plan ID from a previous foresight or decision pipeline run."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedestimate_information_gain3 fields changed
      • addedInput schema / properties / action / description
        Added value: +"The investigation action to evaluate (e.g., \"run_experiment\",\n   \"query_database\", \"interview_stakeholder\")."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedestimate_uncertainty3 fields changed
      • addedInput schema / properties / decision_id / description
        Added value: +"ID of the decision to analyze for uncertainty."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider for calibration (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedevaluate_plan4 fields changed
      • addedInput schema / properties / actions / description
        Added value: +"Ordered list of action descriptions forming the plan (e.g.,\n    [\"analyze requirements\", \"design API\", \"implement\", \"test\"])."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • addedInput schema / properties / max_horizon / description
        Added value: +"Max planning depth (default 5)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedevaluate_scenarios4 fields changed
      • addedInput schema / properties / action / description
        Added value: +"The action the scenarios relate to."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / scenarios / description
        Added value: +"List of custom scenario dicts to evaluate, each containing at\n      minimum 'description' and optionally 'context' and 'outcome'."
    • Changedexplain_decision2 fields changed
      • addedInput schema / properties / plan_id / description
        Added value: +"The plan ID from a previous foresight or decision pipeline run\n    (found in FORESIGHT_EVALUATED event payloads)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedextract_intents2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to analyze (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Addedfail_task
    • Changedgenerate_counterfactual4 fields changed
      • addedInput schema / properties / action / description
        Added value: +"The action description to generate counterfactual alternatives for."
      • addedInput schema / properties / counterfactual_limit / description
        Added value: +"Max number of alternative outcomes to generate (default 3)."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedgenerate_future_plans5 fields changed
      • addedInput schema / properties / action / description
        Added value: +"The action to branch future plans from (starting point)."
      • addedInput schema / properties / foresight_limit / description
        Added value: +"Max number of plan branches to generate (default 5)."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • addedInput schema / properties / max_horizon / description
        Added value: +"Max steps deep into the future per plan (default 5)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedgenerate_scenarios4 fields changed
      • addedInput schema / properties / action / description
        Added value: +"The action to generate possible future scenarios for."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / scenarios_limit / description
        Added value: +"Max number of scenarios to generate (default 4)."
    • Removedget_git_context
    • Removedget_git_status
    • Changedget_observability_dashboard2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to process (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Removedget_recent_changes
    • Changedget_reliability_status2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to analyze (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedget_system_metrics2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to analyze (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedget_task_graph2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider when building the graph (default 5000).\nIncrease for large projects with extensive history."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Removedget_ui_graph_view
    • Removedget_ui_metrics_view
    • Removedget_ui_replay_view
    • Removedget_ui_trace_view
    • Removedget_workflow_graph
    • Removedget_workflow_trace
    • Addedgit_info
    • Changedhandoff_task6 fields changed
      • addedInput schema / properties / from_agent / description
        Added value: +"Current agent handling the task (e.g., \"codex\", \"claude\")."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider for state building (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / reason / description
        Added value: +"Optional reason for the handoff (e.g., \"incomplete context\",\n\"specialized knowledge needed\")."
      • addedInput schema / properties / task_id / description
        Added value: +"ID of the task to hand off."
      • addedInput schema / properties / to_agent / description
        Added value: +"Target agent to hand off to. If None, auto-selects the best-fit\nagent using the same algorithm as `assign_task`."
    • Changedidentify_information_needs3 fields changed
      • addedInput schema / properties / decision_id / description
        Added value: +"ID of the decision whose information needs to analyze."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedlist_events5 fields changed
      • removedInput schema / properties / agent_id
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to return (default 50). Increase for\nbroader history inspection."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / session_id / description
        Added value: +"Optional session ID to filter by (useful for multi-agent\ndebugging and isolation)."
      • addedInput schema / properties / type / description
        Added value: +"Optional event type to filter by (e.g., \"TASK_CREATED\",\n\"TASK_ASSIGNED\", \"TOOL_CALLED\")."
    • Changedobserve_world2 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to process for state reconstruction (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedorchestrate_project4 fields changed
      • addedInput schema / properties / include_git / description
        Added value: +"Whether to include git context in the view (default True)."
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to process (default 10000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / use_snapshot / description
        Added value: +"Whether to use snapshot-based fast resume (default True)."
    • Changedrank_alternatives3 fields changed
      • addedInput schema / properties / actions / description
        Added value: +"List of action descriptions to rank (e.g., [\"deploy v2\", \"rollback\",\n    \"keep current\"])."
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Changedrecommend_policy3 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Max events to consider (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / task / description
        Added value: +"The task definition dict with at minimum a description, and\n optionally required capabilities, priority, and constraints."
    • Addedrenew_task_lease
    • Removedreplay_workflow
    • Changedresolve_conflicts3 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to scan (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / threshold / description
        Added value: +"Similarity threshold for conflict detection (default 0.7)."
    • Changedresume_project4 fields changed
      • addedInput schema / properties / include_git / description
        Added value: +"Whether to include git context in the resume (default True).\nRequires git repository access."
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to process (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / use_snapshot / description
        Added value: +"Whether to use snapshot-based fast resume (default True).\nSet to False to always replay from raw events."
    • Changedresume_with_intent4 fields changed
      • addedInput schema / properties / include_git / description
        Added value: +"Whether to include git context (default True)."
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to process (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / use_snapshot / description
        Added value: +"Whether to use snapshot-based fast resume (default True)."
    • Changedretrieve_memory4 fields changed
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to scan for similarity (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / query / description
        Added value: +"Search query string describing the problem or goal.\nUse natural language; the semantic retriever handles embedding."
      • addedInput schema / properties / top_k / description
        Added value: +"Number of top results to return (default 5, max 50)."
    • Changedrun_decision_pipeline18 fields changed
      • addedInput schema / properties / counterfactual_limit / description
        Added value: +"Max alternative outcomes to generate (default 3)."
      • addedInput schema / properties / enable_counterfactual / description
        Added value: +"Run counterfactual what-if analysis (default False)."
      • addedInput schema / properties / enable_foresight / description
        Added value: +"Run foresight planning (default False)."
      • addedInput schema / properties / enable_information_seeking / description
        Added value: +"Identify information gaps (default False)."
      • addedInput schema / properties / enable_meta_reasoning / description
        Added value: +"Apply meta-reasoning over results (default False)."
      • addedInput schema / properties / enable_scenarios / description
        Added value: +"Run scenario generation (default False)."
      • addedInput schema / properties / enable_uncertainty / description
        Added value: +"Estimate epistemic/aleatoric uncertainty (default False)."
      • addedInput schema / properties / execute_mode / description
        Added value: +"'event_only' (record only), 'queued_runtime' (queue tasks),\n          'simulate', or 'validate' (default 'event_only')."
      • addedInput schema / properties / foresight_limit / description
        Added value: +"Max action chains per branch (default 5)."
      • addedInput schema / properties / limit / description
        Added value: +"Maximum events to process (default 10000)."
      • addedInput schema / properties / max_horizon / description
        Added value: +"Max planning depth (default 5)."
      • addedInput schema / properties / objective / description
        Added value: +"The decision objective dict describing what to decide."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / regret_threshold / description
        Added value: +"Regret threshold 0-1 for counterfactual filtering (default 0.2)."
      • addedInput schema / properties / risk_threshold / description
        Added value: +"Maximum acceptable risk score 0-1 (default 0.7)."
      • addedInput schema / properties / scenario_recommendation_threshold / description
        Added value: +"Min score 0-1 for scenario inclusion (default 0.5)."
      • addedInput schema / properties / scenarios_limit / description
        Added value: +"Max scenarios to generate (default 4)."
      • addedInput schema / properties / simulate_before_execute / description
        Added value: +"Simulate effects before committing (default False)."
    • Changedsave_event12 fields changed
      • removedInput schema / properties / agent_id
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / branch / description
        Added value: +"Optional branch name (for git-based project tracking)."
      • addedInput schema / properties / caused_by / description
        Added value: +"Optional causal event reference (creates event provenance)."
      • addedInput schema / properties / file_path / description
        Added value: +"Optional source file path (for code-related events)."
      • addedInput schema / properties / impact_score / description
        Added value: +"Optional impact score for decision events."
      • addedInput schema / properties / importance / description
        Added value: +"Optional importance rating (1-5); higher values may trigger\nmore frequent snapshots."
      • addedInput schema / properties / payload / description
        Added value: +"Event data as a JSON-serializable dict. Should contain the\nrelevant state or information being recorded."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
      • addedInput schema / properties / session_id / description
        Added value: +"Optional session ID to associate with (for multi-agent tracing)."
      • addedInput schema / properties / source / description
        Added value: +"Event source label (default \"agent\"). Use \"allbrain\" for\nsystem-generated events, or the agent name for agent actions."
      • addedInput schema / properties / task_hint / description
        Added value: +"Optional task hint string (helps with memory building)."
      • addedInput schema / properties / type / description
        Added value: +"Event type identifier (e.g., \"TASK_CREATED\", \"TASK_ASSIGNED\",\n\"TOOL_CALLED\", \"DECISION_MADE\")."
    • Changedsimulate_action3 fields changed
      • addedInput schema / properties / action / description
        Added value: +"Description of the action to simulate (e.g., \"deploy to production\",\n   \"grant admin role to user X\")."
      • addedInput schema / properties / limit / description
        Added value: +"Maximum number of events to process (default 5000)."
      • removedInput schema / properties / project_path
        Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • Addedsummarize_sessions
    • Addedui_view
    • Addedupdate_task
    • Addedworkflow_info
  5. 15 tool updates
    • Addeddetect_knowledge_gaps
    • Addedestimate_confidence
    • Addedestimate_information_gain
    • Addedestimate_uncertainty
    • Addedevaluate_plan
    • Addedevaluate_scenarios
    • Addedexplain_decision
    • Addedgenerate_counterfactual
    • Addedgenerate_future_plans
    • Addedgenerate_scenarios
    • Addedidentify_information_needs
    • Addedobserve_world
    • Addedrank_alternatives
    • Changedrun_decision_pipeline14 fields changed
      • addedInput schema / properties / counterfactual_limit
        Added value: +{
+  "default": 3,
+  "type": "integer"
+}
      • addedInput schema / properties / enable_counterfactual
        Added value: +{
+  "default": false,
+  "type": "boolean"
+}
      • addedInput schema / properties / enable_foresight
        Added value: +{
+  "default": false,
+  "type": "boolean"
+}
      • addedInput schema / properties / enable_information_seeking
        Added value: +{
+  "default": false,
+  "type": "boolean"
+}
      • addedInput schema / properties / enable_meta_reasoning
        Added value: +{
+  "default": false,
+  "type": "boolean"
+}
      • addedInput schema / properties / enable_scenarios
        Added value: +{
+  "default": false,
+  "type": "boolean"
+}
      • addedInput schema / properties / enable_uncertainty
        Added value: +{
+  "default": false,
+  "type": "boolean"
+}
      • addedInput schema / properties / foresight_limit
        Added value: +{
+  "default": 5,
+  "type": "integer"
+}
      • addedInput schema / properties / max_horizon
        Added value: +{
+  "default": 5,
+  "type": "integer"
+}
      • addedInput schema / properties / regret_threshold
        Added value: +{
+  "default": 0.2,
+  "type": "number"
+}
      • addedInput schema / properties / risk_threshold
        Added value: +{
+  "default": 0.7,
+  "type": "number"
+}
      • addedInput schema / properties / scenario_recommendation_threshold
        Added value: +{
+  "default": 0.5,
+  "type": "number"
+}
      • addedInput schema / properties / scenarios_limit
        Added value: +{
+  "default": 4,
+  "type": "integer"
+}
      • addedInput schema / properties / simulate_before_execute
        Added value: +{
+  "default": false,
+  "type": "boolean"
+}
    • Addedsimulate_action
  6. 34 tool updatesv0.1.0
    • First observedadd_task_dependency
    • First observedassign_task
    • First observedbuild_memory
    • First observedchange_task_priority
    • First observedcompare_agents
    • First observedcreate_snapshot
    • First observedcreate_task
    • First observeddetect_conflicts
    • First observeddetect_contradictions
    • First observedextract_intents
    • First observedget_git_context
    • First observedget_git_status
    • First observedget_observability_dashboard
    • First observedget_recent_changes
    • First observedget_reliability_status
    • First observedget_system_metrics
    • First observedget_task_graph
    • First observedget_ui_graph_view
    • First observedget_ui_metrics_view
    • First observedget_ui_replay_view
    • First observedget_ui_trace_view
    • First observedget_workflow_graph
    • First observedget_workflow_trace
    • First observedhandoff_task
    • First observedlist_events
    • First observedorchestrate_project
    • First observedrecommend_policy
    • First observedreplay_workflow
    • First observedresolve_conflicts
    • First observedresume_project
    • First observedresume_with_intent
    • First observedretrieve_memory
    • First observedrun_decision_pipeline
    • First observedsave_event
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct function: event logging (save/list), git context, semantic memory retrieval, and task creation. There is no overlap or ambiguity in their purposes.

Naming Consistency3/5

Most tools follow a verb_noun pattern (save_event, list_events, retrieve_memory, create_task), but git_info breaks this pattern as a noun phrase, introducing inconsistency.

Tool Count4/5

With 5 tools covering event log, git, memory, and tasks, the count is within the typical 3-15 range but feels slightly thin given the broad scope, making it reasonable but not well-scoped.

Completeness3/5

The event log is complete with save and list, but git lacks write operations, memory lacks a creation tool (build_memory is referenced but not present), and tasks lack update, delete, or list operations, leaving notable gaps.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Context Manager

    transparentlyok
    A
    license
    A
    quality
    D
    maintenance
    Enables efficient code navigation and retrieval through natural language search, BM25 ranking, and fuzzy matching across multiple programming languages. It drastically reduces token usage by allowing Claude to query specific code symbols and logic instead of reading entire files.
    13
    70 npm
    13
    MIT

  • MEMGRAPH-MCP

    MikeB317
    F
    license
    A
    quality
    D
    maintenance
    A durable multi-agent orchestrator for software development with explicit run graphs, checkpoint/resume capabilities, and project memory exposed through MCP resources and tools. It enables coordinated agent workflows for coding, review, repair, CI, and approval with SQLite-backed memory retrieval and pluggable research backends.
    10
    -