Longhand
PYPI · LONGHAND · SCANNED SEP 20
Local memory for Claude Code. Semantic recall across session history with zero API calls.
Available components
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 Security24
- Malware scan not yet available for this package.Unverified
- A critical CVE affects chromadb, and no fixed version has been published yet. View diagnostics → Fail
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 8 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 2 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability77
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1791 tokens (~105/item across 17 items; 17 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 76% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Longhand MCP server?
Longhand runs locally as a PyPI package, launched with uvx longhand. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · longhand
claude mcp add wynelson94-longhand -- uvx longhand
{
"mcpServers": {
"wynelson94-longhand": {
"command": "uvx",
"args": [
"longhand"
]
}
}
} {
"servers": {
"wynelson94-longhand": {
"command": "uvx",
"args": [
"longhand"
]
}
}
} codex mcp add wynelson94-longhand -- uvx longhand
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"wynelson94-longhand": {
"type": "local",
"command": [
"uvx",
"longhand"
],
"enabled": true
}
}
} openclaw mcp add wynelson94-longhand --command uvx --arg longhand
mcp_servers:
wynelson94-longhand:
command: "uvx"
args: ["longhand"] {
"McpServers": {
"wynelson94-longhand": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"longhand"
]
}
}
} assistant mcp add wynelson94-longhand -t stdio -c uvx -a longhand
{
"mcpServers": {
"wynelson94-longhand": {
"command": "uvx",
"args": [
"longhand"
]
}
}
} 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.
- 19 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.
- 18 Sept 26 −18
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.80 functional
- 17 Sept 26 0
- Stability: 0.97 → pass security
- 16 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 12 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.
- 11 Sept 26 −3
- Stability: pass → 0.80 functional
- 10 Sept 26 0
- Stability: 0.97 → pass security
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/longhand@0.5.5
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 | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Vulnerabilities 8 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-2wm9-hf6c-p5cr | CVE-2026-45830 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | no |
| GHSA-36p7-vc44-83pf | CVE-2026-45833 | critical | no | |
| GHSA-f4j7-r4q5-qw2c | CVE-2026-45829 | critical | no | |
| GHSA-xph7-9rjv-w5fr | CVE-2026-45831 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | no |
| PYSEC-2026-311 | CVE-2026-45829 | none | no | |
| PYSEC-2026-3813 | CVE-2026-45830 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | no |
| PYSEC-2026-3814 | CVE-2026-45833 | none | no | |
| PYSEC-2026-3815 | CVE-2026-45831 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | no |
Background: What a vulnerability scan can and cannot prove →
Dependencies 92 packages
| Packages resolved | 92 |
|---|---|
| Stale | 8 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
find_commits ~112
Search across all sessions for git commits matching a query — by commit message, hash prefix, or branch name. Great for 'find that commit where we fixed the parser' queries.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | – | – | Max results |
| max_chars | – | – | Max output characters |
| operation_type | string | – | Filter by operation type (default: all) |
| query | string | yes | Commit message substring, hash prefix, or branch name |
| session_id | string | – | Optional: scope to a single session (prefix match) |
No output schema declared.
No examples provided.
find_episodes ~102
Structured search for problem→fix episodes. Filters: project_ids, time range, keyword, has_fix. Returns raw episode rows. Use this when you already know the project or want data instead of narrative.
| Name | Type | Req | Description |
|---|---|---|---|
| has_fix | boolean | – | – |
| keyword | string | – | – |
| limit | – | – | Max results (default 20) |
| project_ids | array | – | – |
| since | string | – | ISO timestamp |
| until | string | – | ISO timestamp |
No output schema declared.
No examples provided.
get_episode ~53
Full detail for one episode by episode_id. Includes all referenced events (problem, diagnosis thinking block, fix edit, verification), the diff, and the reconstructed file state after the fix.
| Name | Type | Req | Description |
|---|---|---|---|
| episode_id | string | yes | – |
No output schema declared.
No examples provided.
get_file_history ~47
Get every edit ever made to a file across all sessions, chronologically.
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | – |
| session_id | string | – | Optional: limit to a single session |
No output schema declared.
No examples provided.
get_latest_events ~136
Get the N most recent events in a session, in reverse chronological order (sequence DESC). Use this when you need 'what was the latest X' — e.g., the last user message, the last tool call, the last assistant response. Semantic search is the wrong tool for recency; this one is. Supports session id prefix match.
| Name | Type | Req | Description |
|---|---|---|---|
| event_type | string | – | Optional: filter to a single event type (user_message, assistant_text, tool_call, etc.) |
| limit | – | – | Max events to return (default 10) |
| max_chars | – | – | Max total output characters |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
get_project_timeline ~81
Session-level timeline for a project. Returns recent sessions with their outcomes (shipped / fixed / stuck / exploratory) for a bird's-eye view of what's been happening in a project lately.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | – | – | Max results (default 50) |
| project_id | string | yes | – |
| since | string | – | – |
| until | string | – | – |
No output schema declared.
No examples provided.
get_session_commits ~100
Get all git operations (commits, pushes, merges, checkouts, etc.) from a session, chronologically. Links session work to git history — the in-between that git log doesn't capture.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | – | – | Max results |
| max_chars | – | – | Max output characters |
| operation_type | string | – | Filter: commit, push, pull, checkout, merge, etc. |
| session_id | string | yes | Session ID (prefix match) |
No output schema declared.
No examples provided.
get_session_timeline ~193
Get a chronological timeline of events in a session. Supports session id prefix match. Use 'tail' to get only the last N events (great for checking how a session ended). Use 'offset' to paginate through long sessions. NOT for searching — if you're looking for something specific in a session, use search_in_context instead of paginating this tool in a loop.
| Name | Type | Req | Description |
|---|---|---|---|
| event_type | string | – | Filter to a single event type |
| include_thinking | boolean | – | – |
| limit | – | – | Max events to return (default 100) |
| max_chars | – | – | Max total output characters |
| offset | – | – | Skip first N events (for pagination) |
| session_id | string | yes | – |
| summary_only | boolean | – | Return only event_type, timestamp, tool_name, file_path — no content. Great for scanning long sessions. |
| tail | – | – | Return only the last N events of the session |
No output schema declared.
No examples provided.
get_stats ~15
Get overall Longhand storage statistics.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_projects ~76
Browse inferred projects by keyword, category, or recency. Returns compact summaries by default. Set verbose=true for full detail.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| keyword | string | – | – |
| limit | – | – | Max results (default 20) |
| verbose | boolean | – | Return full project rows including aliases, keywords, languages JSON |
No output schema declared.
No examples provided.
list_sessions ~42
List recent Claude Code sessions that Longhand has indexed.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | – | – | Max results (default 20) |
| project | string | – | Filter by project path substring |
No output schema declared.
No examples provided.
match_project ~64
Fuzzy project matching. Given a partial project name, category, or description, returns candidate projects with match reasons. Useful for confirming 'which game did you mean?' before drilling into episodes.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
| top_k | – | – | Max project matches to return |
No output schema declared.
No examples provided.
recall ~121
PROACTIVE MEMORY — START HERE for any 'do you remember...' question. Handles fuzzy time references ('a couple months ago'), project matching ('that game project'), and episode retrieval in ONE call. Returns: matched projects, relevant episodes (problem→fix pairs), diffs, verbatim thinking blocks, reconstructed file states, and a prebuilt markdown narrative. Do NOT manually search and paginate — use this tool first.
| Name | Type | Req | Description |
|---|---|---|---|
| max_chars | – | – | Max total output characters |
| max_episodes | – | – | Max episodes to return |
| query | string | yes | Natural language question |
No output schema declared.
No examples provided.
recall_project_status ~139
Get the current status of a project — where you left off, recent commits, unresolved issues, and latest conversation context. Takes a project name (fuzzy match) and returns a structured summary with git history, linked episodes, and conversation segments. Use this when someone says 'pick up where we left off on X', 'what's the status of X', or 'where did we end on X'.
| Name | Type | Req | Description |
|---|---|---|---|
| max_chars | – | – | Max output characters |
| max_commits | – | – | Max recent commits to show |
| max_episodes | – | – | Max recent episodes |
| project | string | yes | Project name, alias, or ID (fuzzy match) |
No output schema declared.
No examples provided.
replay_file ~72
Reconstruct the state of a file at a point in a past Claude Code session. Applies every edit verbatim from the session JSONL — no summarization.
| Name | Type | Req | Description |
|---|---|---|---|
| at_event_id | string | – | Optional: reconstruct up to this event |
| file_path | string | yes | – |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
search ~259
Semantic search across all stored Claude Code session events. Returns events matching a natural language query, with optional filters by event type, session, project, tool, or file path. IMPORTANT: Always pass session_id when you know which session to search — unscoped search returns noisy results. For finding a discussion WITH surrounding conversation context, use search_in_context instead.
| Name | Type | Req | Description |
|---|---|---|---|
| event_type | string | – | Filter: user_message, assistant_text, assistant_thinking, tool_call, tool_result |
| file_path_contains | string | – | Filter to events with an explicit file_path containing this string (tool_call/tool_result events only — user messages won't have file_path metadata) |
| limit | – | – | Max results (default 10) |
| max_chars | – | – | Max total output characters (default 12000). Set higher if you need full content. |
| project_id | string | – | Scope search to a project by project_id |
| project_name | string | – | Scope search to a project by name substring (e.g. 'gonzo') |
| query | string | yes | Natural language query |
| session_id | string | – | Scope search to a single session (prefix match) |
| tool_name | string | – | Filter by tool name (Edit, Bash, Read, etc.) |
No output schema declared.
No examples provided.
search_in_context ~179
Search within a specific session and return matches WITH surrounding conversation context. This is the tool you want when you know WHICH session to look in but need to FIND a specific discussion or event. Returns each semantic match plus N events before/after it from the timeline, so you can read the full conversation flow. Much more efficient than paginating get_session_timeline manually.
| Name | Type | Req | Description |
|---|---|---|---|
| context_events | – | – | Number of events to include before AND after each match (default 5) |
| event_type | string | – | Optional: filter matches to a single event type |
| limit | – | – | Max number of matches to return with context (default 3) |
| max_chars | – | – | Max total output characters (default 20000) |
| query | string | yes | Natural language query to find within the session |
| session_id | string | yes | Session ID (prefix match) |
No output schema declared.
No examples provided.
What is the Longhand MCP server?
Longhand is an MCP server listed in the public MCP registry as io.github.Wynelson94/longhand. Local memory for Claude Code. Semantic recall across session history with zero API calls. This page covers its PyPI package (longhand).
Is the Longhand MCP server safe to use?
Longhand scores 60 out of 100 on VerifyMCP. We recorded 8 known advisories against 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 Longhand MCP server expose?
Longhand exposes 17 tools: search, search_in_context, list_sessions, get_session_timeline, get_latest_events, and 12 more. Their descriptions and schemas cost roughly 1,791 tokens of context every time the server is loaded.
Is the Longhand MCP server still maintained?
Longhand 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 Longhand MCP server under?
Longhand declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.