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.

io.github.clauderecallhq/recall

NPM · @CLAUDERECALLHQ/CLI · SCANNED SEP 20

Persistent memory for Claude Code. Search, recall, and re-inject context from any session.

Available components

0 this week 73 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 Security89
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects sharp 0.34.5, reached via @huggingface/transformers > sharp. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 78 of 229 dependencies flagged as unhealthy (2 deprecated). View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability87
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 852 tokens (~65/item across 13 items; 13 tools + 0 resources), lean.Pass
  • 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 Coverage96
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 88% 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 13 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
Install

How do I install the io.github.clauderecallhq/recall MCP server?

io.github.clauderecallhq/recall runs locally as an npm package, launched with npx -y @clauderecallhq/cli. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @clauderecallhq/cli

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

  • 13 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.

  • 12 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 11 Sept 26 0
    • Stability: 0.97 → pass security
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 npm/@clauderecallhq/cli@0.12.0

Provenance No attestation

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

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 2 findings
ID CVE Severity Vector Fix available
GHSA-f88m-g3jw-g9cj high yes
GHSA-rgj7-g3m4-5g8c high yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 229 packages
Packages resolved 229
Deprecated 2
Stale 77
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~852 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
apply_tags ~87

Add one or more tags to a session (merge-mode, never removes existing). Only works when auto-tagging is enabled. Accepts full UUID or 8+-character id prefix.

NameTypeReqDescription
sessionIdstringyesFull session UUID or 8+-character prefix.
tagsarrayyesTags to add. Normalized server-side (lowercase, hyphens, strip #).

No output schema declared.

No examples provided.

context_for_session ~134

Render a past session as markdown ready to paste into a fresh Claude conversation. This is the flagship Recall operation: pipe any previous session back into a new chat as memory.

NameTypeReqDescription
idstringyesSession id (full UUID or 8+-character prefix).
includeSidechainbooleanInclude subagent / sidechain messages (default false).
modestring`condensed` (default) strips tool-call JSON; `full` keeps everything.
preludestringOptional header prepended above the transcript.
sincestringOnly messages at or after this ISO timestamp.

No output schema declared.

No examples provided.

find_similar_sessions ~81

Find sessions semantically similar to a given session using vector embeddings (Pro-only). Returns related sessions ranked by cosine similarity.

NameTypeReqDescription
limitintegerMax results (default 10).
min_cosinenumberMinimum cosine similarity threshold (default 0.65).
session_idstringyesSession ID to find similar sessions for.

No output schema declared.

No examples provided.

get_session ~51

Return the full metadata and ordered messages for a session. Accepts a full UUID or an 8+-character id prefix.

NameTypeReqDescription
idstringyesSession id (full UUID or 8+-character prefix).

No output schema declared.

No examples provided.

list_projects ~29

Every Claude Code project currently indexed by Recall, with session and message counts and the most recent activity timestamp.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_sessions ~112

Recent sessions with alias, tags, and message counts. Optional filters for project, tag, and date range.

NameTypeReqDescription
limitinteger
projectstringSubstring match against project name or decoded filesystem path.
sincestringOnly sessions started at or after this ISO timestamp or YYYY-MM-DD date.
tagstringOnly sessions carrying this tag (leading # optional).
untilstringOnly sessions started at or before this ISO timestamp or YYYY-MM-DD date.

No output schema declared.

No examples provided.

list_sessions_to_tag ~98

Return session summaries and sampled messages formatted for an agent to propose tags. Respects the same scope filters used by the Recall UI scan. Only returns data if auto-tagging is enabled in config.

NameTypeReqDescription
collectionIdstringOnly sessions in this collection.
limitinteger
projectstringExact project name match.
untaggedOnlybooleanOnly sessions with zero tags (default false).

No output schema declared.

No examples provided.

list_tags ~24

Every tag currently applied to a session, with its count, most popular first.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

search ~90

Full-text search over every message in every indexed session. Use `#tag-name` tokens inside the query string to also filter by tag; plain terms are ANDed together.

NameTypeReqDescription
limitinteger
projectstringSubstring match against project name or path.
querystringyesText to find. Supports inline `#tag-name` tokens to narrow to sessions with the tag.

No output schema declared.

No examples provided.

semantic_status ~26

Health snapshot of the semantic vector search tier: model status, worker status, queue depth.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

thread_for_session ~41

Return non-archived threads that reference this session (as origin or child).

NameTypeReqDescription
session_idstringyesSession UUID (exact, not a prefix).

No output schema declared.

No examples provided.

thread_get ~31

Full thread detail including every session edge (origin + children).

NameTypeReqDescription
idstringyesThread id (UUID).

No output schema declared.

No examples provided.

thread_list ~48

All threads (v0.15a intent groups), newest first. Excludes archived threads unless include_archived is true.

NameTypeReqDescription
include_archivedbooleanInclude archived threads (default false).

No output schema declared.

No examples provided.

Common questions

What is the io.github.clauderecallhq/recall MCP server?

io.github.clauderecallhq/recall is an MCP server listed in the public MCP registry as io.github.clauderecallhq/recall. Persistent memory for Claude Code. Search, recall, and re-inject context from any session. This page covers its npm package (@clauderecallhq/cli).

Is the io.github.clauderecallhq/recall MCP server safe to use?

io.github.clauderecallhq/recall scores 73 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 20 September 2026. It declares no install or post-install scripts. 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 io.github.clauderecallhq/recall MCP server expose?

io.github.clauderecallhq/recall exposes 13 tools: list_projects, list_sessions, list_tags, list_sessions_to_tag, apply_tags, and 8 more. Their descriptions and schemas cost roughly 852 tokens of context every time the server is loaded.

Is the io.github.clauderecallhq/recall MCP server still maintained?

io.github.clauderecallhq/recall 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.