Skip to main content

DSM Memory MCP Server — provable, append-only memory for AI agents via MCP

Project description

DSM MCP Server

Provable, append-only memory for AI agents via MCP.

Install

pip install dsm-mcp

Run

dsm-mcp
# or
python -m dsm.integrations.goose

Configure with Goose

Add to ~/.config/goose/extensions.d/dsm-memory.yaml:

name: dsm-memory
type: stdio
cmd: dsm-mcp

What it does

DSM records every agent action in an append-only SHA-256 hash chain. Nothing can be deleted, reordered, or tampered with without detection.

11 MCP tools: dsm_status, dsm_start_session, dsm_end_session, dsm_log_action, dsm_confirm_action, dsm_snapshot, dsm_recall, dsm_recent, dsm_summary, dsm_search, dsm_verify.

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dsm_mcp-0.1.1.tar.gz (1.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dsm_mcp-0.1.1-py3-none-any.whl (1.7 kB view details)

Uploaded Python 3

File details

Details for the file dsm_mcp-0.1.1.tar.gz.

File metadata

  • Download URL: dsm_mcp-0.1.1.tar.gz
  • Upload date:
  • Size: 1.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for dsm_mcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 478838027e36848466c4b56c507a8085816faafab6a65948ef90dacc6b3266ad
MD5 866c2d6704edfd5e4d45cf22bee950c7
BLAKE2b-256 d5858b9dbc1ecbe92d1f68f4962d1fd6153a92761602e3c60f85de4ff9c75a58

See more details on using hashes here.

Provenance

The following attestation bundles were made for dsm_mcp-0.1.1.tar.gz:

Publisher: publish-pypi.yml on daryl-labs-ai/daryl

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file dsm_mcp-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: dsm_mcp-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 1.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for dsm_mcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 74baf5ce06e386e403a27658c86d1637bc58978ac0e2b15ee2d2371a81007230
MD5 c37577a8eb48ba74d1fc2dd3b996da63
BLAKE2b-256 94f3739c7fecf60bd4a6437ae4a49422e598e95b8a481a6ee68fc3646d57ee4f

See more details on using hashes here.

Provenance

The following attestation bundles were made for dsm_mcp-0.1.1-py3-none-any.whl:

Publisher: publish-pypi.yml on daryl-labs-ai/daryl

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page