Skip to main content

MCP server

AgentDesk runs a built-in Model Context Protocol server that exposes a project's shared memory to any AI client. This is how Claude Code, Codex, Gemini and web clients read and write the same project brain.

Transports

All clients connect to the hosted server over HTTP/SSE — GET /mcp/sse?project={name} and POST /mcp/messages, authenticated with an ad_ integration key. AgentDesk registers the server per project in a .mcp.json file, so each project exposes its own memory.

Tools

The server exposes tools across memory, history, work items, code and git. Read-only tools fetch context; mutating tools (marked ) change state.

Memory & context

ToolPurpose
search_memoryHybrid search across work items + events (semantic + keyword + relationship graph, rank-fused)
record_eventWrite a structured fact into memory
pin_factPin an explicit rule — project-wide or scoped to one code folder — always injected into context
bootstrap_sessionLoad conventions, policies and components for a session
get_session_tags / set_session_tagsRead / update the current session's phase, feature, bug ref

History

ToolPurpose
get_recent_historyLast N prompt/response pairs
get_commitsCommits tagged by phase / feature / bug
get_work_item_historyLinked prompts + commits for a work item
get_file_historySymbol-level changes for a file

Work items

ToolPurpose
create_entityCreate a draft work item
list_work_itemsFilter by type / status / due date
get_item_by_numberResolve BU0001 / FE0002 to full detail
update_work_itemChange status or score
record_work_logRecord delivery, verification and commit provenance against an item/use case
run_work_item_pipelineAI-summarise an approved item

Code & git

ToolPurpose
get_code_symbolsCyclomatic complexity + hotspot scores
get_db_schemaFull database schema dump
commit_pushStage, commit and push from any IDE

Skills

ToolPurpose
get_skillSkill definition + project context
run_skillExecute a skill (same flow as the web UI)

Example: Claude Code

Point Claude Code at the project's MCP server and it can search memory, read history and commit — all sharing the same brain as your other tools. A common first call is bootstrap_session (to load current conventions, facts and open work) followed by search_memory for whatever you're working on. At the end of implementation, agents can call record_work_log so the use case and generated OKF bundle show what changed.

Other MCP clients

Any MCP-capable agent can use the same server — Cursor, Cline, Roo Code, Windsurf, Zed, Continue.dev, Goose, OpenCode, Warp and Claude Desktop all connect with the standard mcpServers block; only the config-file location differs per client. The desktop app's External Skills & MCP view has a per-client setup card with a copy-paste config and the client's quirks.

Capture hooks (prompt, session and tool-observation logging) remain a Claude Code / Codex / Gemini feature; MCP-only clients get the full tool set without passive capture.

Not the same as AgentData's MCP

This server exposes a codebase's project memory. AgentData's MCP server exposes a database's semantic model. Different tools, same protocol.

Next: Shared prompts →