DocDeploy

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/www-docdeploy-io-mcp-server

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

11 read · 1 write · 1 delete · 2 not yet classified

Secrets

None asked for

Install scripts

Nothing to install (hosted)

Runs as

Hosted (remote endpoint)

Tools (15)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• forget_memory

  Delete a memory by its slug for a principal.

• get_document

  Retrieve a full document with all its sections.

• get_manifest

  Get a high-level manifest of every document and its section table of contents.

• get_memory_preferences

  FREE. Returns the resolved memory write cadence for the principal: { mode (off|manual|nudge|auto), triggers (afterTurns, afterTokens, afterMinutes, onTaskComplete), source, layers, contract }. Call ONCE per session before deciding when to write memories — the contract field is the rulebook for honoring the user's preference.

• get_memory_schema

  FREE. Returns Doc Deploy Memory Schema v1: kind taxonomy, frontmatter shape, link conventions, entity taxonomy, and a fully-worked example. Call before your first remember_memory to write well-structured, dedupe-friendly entries.

• get_original_url

  Get a presigned URL to download the original binary of a document.

• get_section

  Retrieve a single section of a document by section index.

• list_documents

  List all documents available to the current tenant (metadata only).

• list_memories

  List a principal's memories without decrypting bodies.

• recall_memory

  Recall memories for a principal. Filter by domain, slug, kind, tag, or linkedTo (URI). Free-text query matches title + context + keywords + frontmatter. Returns content + resolved links graph + entities.

• remember_memory

  Persist a structured agent memory using Memory Schema v1. Markdown with YAML frontmatter (kind, title, domain, source, links, entities, ...). Content is AES-256-GCM encrypted; frontmatter is indexed unencrypted. Slug auto-derives from sha1(kind|title|body) for free dedupe. Call get_memory_schema first for the canonical example.

• report_document_structure

  Report the detected document structure as an array of sections.

• search_documents

  Search documents by query text. Matches against document titles, section titles, and section content.

• set_memory_preferences

  FREE. Set the memory write cadence for a principal (or, with scope='tenant', for the whole tenant). Agent should ONLY call this when the user explicitly says 'stop asking me before saving memories' (mode=auto), 'only save when I tell you to' (mode=manual), 'save more often' (triggers.afterTurns=5), etc. Pass preference=null to clear and fall back to the next layer.

• whoami

  FREE. Returns the tenant + default principal this MCP connection resolves to, plus the client label the agent is seen as, linked wallets/DIDs, and the current memory write cadence. Agents should call this ONCE per session before any memory read/write so multi-agent tenants sharing a single MCP API key get consistent principal strings and source_agent attribution.

Signals

Stars

0

Forks

0

Open issues

0

Last commit

Apr 16, 2026 (6 months ago)

Last release

Apr 12, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.docdeploy.www/mcp-server

Version

1.0.0

Auth

Auth not stated

License

License unknown

Repository

github.com/mrdulasolutions/docdeploy

Website

docdeploy.io

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql