Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

TeamMemory

PYPI · TEAM_MEMORY · SCANNED SEP 20

Team experience database - let AI accumulate, retrieve and apply team knowledge across chats.

Available components

−15 this week 68 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 41 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability81
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1823 tokens (~113/item across 16 items; 13 tools + 3 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage95
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 84% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the TeamMemory MCP server?

TeamMemory runs locally as a PyPI package, launched with uvx team_memory. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · team_memory

# add to Claude Code
claude mcp add ysydhc-team-memory -- uvx team_memory
// .cursor/mcp.json
{
  "mcpServers": {
    "ysydhc-team-memory": {
      "command": "uvx",
      "args": [
        "team_memory"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ysydhc-team-memory": {
      "command": "uvx",
      "args": [
        "team_memory"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add ysydhc-team-memory -- uvx team_memory
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ysydhc-team-memory": {
      "type": "local",
      "command": [
        "uvx",
        "team_memory"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ysydhc-team-memory --command uvx --arg team_memory
# ~/.hermes/config.yaml
mcp_servers:
  ysydhc-team-memory:
    command: "uvx"
    args: ["team_memory"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ysydhc-team-memory": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "team_memory"
      ]
    }
  }
}
# add to Vellum
assistant mcp add ysydhc-team-memory -t stdio -c uvx -a team_memory
// mcp.json
{
  "mcpServers": {
    "ysydhc-team-memory": {
      "command": "uvx",
      "args": [
        "team_memory"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 18 Sept 26 0
    • Stability: 0.97 → pass security
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 +16
    • Malware scan: unverified → pass security
  • 12 Sept 26 −3
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/team_memory@0.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 41 packages
Packages resolved 41
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~1,524 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
tm_claim ~56

Claim an experience/problem so other agents know you're working on it. Claims auto-expire after 30 minutes of inactivity.

NameTypeReqDescription
experience_idstringyesThe experience ID to claim.
messageOptional message describing what you're doing.
NameTypeReqDescription
resultstringyes

No examples provided.

tm_config ~22

Read runtime retrieval configuration snapshot (retrieval/search/cache/pageindex-lite).

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

tm_feedback ~78

Provide feedback on a searched experience — rate 1-5 (5=best). This improves future search results. Returns ~50 tokens.

NameTypeReqDescription
commentOptional feedback comment.
experience_idstringyesThe ID of the experience to rate.
ratingintegeryesRating from 1 to 5 (5 = most helpful).
NameTypeReqDescription
resultstringyes

No examples provided.

tm_learn ~134

Learn from a conversation or document: extract structured experience using LLM and auto-save to the knowledge base. Call this after solving a problem to capture the knowledge. By default saves as draft (requires review before publishing). Returns ~200-500 tokens.

NameTypeReqDescription
as_groupbooleanIf True, extract as parent + children experience group.
conversationstringyesThe conversation or document text to learn from (required).
project
save_as_draftbooleanIf True (default), save as draft requiring review.
tagsAdditional tags to merge with LLM-extracted tags.
NameTypeReqDescription
resultstringyes

No examples provided.

tm_notify ~57

Notify the team that a new experience has been saved. Use after tm_save or tm_learn to signal other agents.

NameTypeReqDescription
experience_idstringyesThe experience ID to notify about.
messagestringHuman-readable notification message.
NameTypeReqDescription
resultstringyes

No examples provided.

tm_save ~172

Quick-save a simple experience (title + problem required, solution optional). Use this for fast knowledge capture — solution can be added later. For typed experiences with full fields, use tm_save_typed instead. Returns ~100-200 tokens.

NameTypeReqDescription
code_snippetsKey code examples.
frameworkFramework.
languageProgramming language.
problemstringyesProblem description (required).
project
publish_statusstring"published" (default) or "draft".
root_causeRoot cause analysis.
skip_dedupbooleanIf True, skip duplicate detection check.
solutionSolution description (optional — allows incomplete experiences).
tagsTags for the experience.
titlestringyesExperience title (required).
NameTypeReqDescription
resultstringyes

No examples provided.

tm_save_group ~200

Save a group of related experiences (parent + children). Use this when a solution involves multiple steps or stages. The parent describes the overall problem/solution, children describe individual steps. Returns ~200-500 tokens.

NameTypeReqDescription
categoryCategory classification.
childrenarrayyesList of dicts, each with keys: title, problem, solution, and optionally: tags, code_snippets, root_cause.
experience_typestringType for the group (default "general").
frameworkFramework.
languageProgramming language.
parent_problemstringyesProblem description for the parent.
parent_root_causeRoot cause for the parent.
parent_solutionOverall solution summary (optional).
parent_tagsTags for the parent.
parent_titlestringyesTitle for the parent experience.
project
severitySeverity for bugfix/incident groups.
NameTypeReqDescription
resultstringyes

No examples provided.

tm_save_typed ~322

Save a typed experience with full fields (experience_type, severity, category, structured_data, git_refs, related_links, progress_status). Types: general, feature, bugfix, tech_design, incident, best_practice, learning. Returns ~200-400 tokens.

NameTypeReqDescription
categoryCategory (frontend/backend/database/infra/performance/security/other).
code_snippetsKey code examples.
experience_typestringType — general/feature/bugfix/tech_design/incident/best_practice/learning.
frameworkFramework.
git_refsList of git references [{type, url, hash, description}].
languageProgramming language.
problemstringyesProblem description (required).
progress_statusProgress status (type-specific, e.g., open/investigating/fixed/verified).
project
publish_statusstring"published" (default) or "draft".
related_linksList of related links [{type, url, title}].
root_causeRoot cause analysis.
severitySeverity level (P0-P4, for bugfix/incident).
skip_dedupbooleanIf True, skip duplicate detection check.
solutionSolution (optional — allows incomplete experiences).
structured_dataType-specific data dict (e.g., reproduction_steps, environment for bugfix).
tagsTags for the experience.
titlestringyesExperience title (required).
NameTypeReqDescription
resultstringyes

No examples provided.

tm_search ~145

Search the team experience database for relevant solutions. Call this BEFORE starting to solve a technical problem to check if the team already has a solution. Returns ~1000-4000 tokens depending on result count.

NameTypeReqDescription
groupedbooleanReturn results grouped by parent-child. Default True.
max_resultsintegerMaximum number of results (or groups when grouped=True).
min_similaritynumberMinimum similarity threshold.
project
querystringyesThe search query.
tagsOptional tags to filter by.
top_k_childrenintegerMax children per group. Default 3.
use_pageindex_lite
NameTypeReqDescription
resultstringyes

No examples provided.

tm_solve ~139

Smart problem solving: search the team experience database, auto-format the best solution, and mark it as used. Call this FIRST when encountering a technical problem. Returns ~500-2000 tokens (focused on top matches).

NameTypeReqDescription
file_pathCurrent file path for context enrichment.
frameworkFramework for filtering.
languageProgramming language for filtering.
max_resultsintegerMax solutions to return (default 3, focused).
problemstringyesDescription of the problem to solve (required).
project
tagsOptional tags to filter by.
use_pageindex_lite
NameTypeReqDescription
resultstringyes

No examples provided.

tm_status ~24

Read runtime status summary for diagnostics (service/search-pipeline/cache/pageindex-lite).

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

tm_suggest ~128

Get experience recommendations based on current work context. Unlike tm_search which needs an explicit query, tm_suggest builds a query from file path, language, framework, or error message. Returns ~500-2000 tokens (lightweight format).

NameTypeReqDescription
error_messageError message encountered (if any).
file_pathCurrent file path (extracts directory/filename hints).
frameworkFramework being used.
languageProgramming language being used.
max_resultsintegerMaximum suggestions to return.
project
use_pageindex_lite
NameTypeReqDescription
resultstringyes

No examples provided.

tm_update ~47

Update an existing experience with additional solution details or new tags. Returns ~100-300 tokens.

NameTypeReqDescription
experience_idstringyes
solution_addendum
tags
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the TeamMemory MCP server?

TeamMemory is an MCP server listed in the public MCP registry as io.github.ysydhc/team-memory. Team experience database - let AI accumulate, retrieve and apply team knowledge across chats. This page covers its PyPI package (team_memory).

Is the TeamMemory MCP server safe to use?

TeamMemory scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the TeamMemory MCP server expose?

TeamMemory exposes 13 tools: tm_solve, tm_learn, tm_suggest, tm_search, tm_save, and 8 more. Their descriptions and schemas cost roughly 1,524 tokens of context every time the server is loaded.

Is the TeamMemory MCP server still maintained?

TeamMemory is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the TeamMemory MCP server under?

TeamMemory declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.