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.

Session Forge

NPM · SESSION-FORGE · SCANNED SEP 20

Persistent memory and session intelligence for AI coding assistants. Zero config.

Available components

0 this week 80 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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1298 tokens (~86/item across 15 items; 15 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 Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "data_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • 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 supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Session Forge MCP server?

Session Forge runs locally as an npm package, launched with npx -y session-forge. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · session-forge

# add to Claude Code
claude mcp add 420247jake-session-forge -- npx -y session-forge
// .cursor/mcp.json
{
  "mcpServers": {
    "420247jake-session-forge": {
      "command": "npx",
      "args": [
        "-y",
        "session-forge"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "420247jake-session-forge": {
      "command": "npx",
      "args": [
        "-y",
        "session-forge"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add 420247jake-session-forge -- npx -y session-forge
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "420247jake-session-forge": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "session-forge"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add 420247jake-session-forge --command npx --arg -y --arg session-forge
# ~/.hermes/config.yaml
mcp_servers:
  420247jake-session-forge:
    command: "npx"
    args: ["-y", "session-forge"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "420247jake-session-forge": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "session-forge"
      ]
    }
  }
}
# add to Vellum
assistant mcp add 420247jake-session-forge -t stdio -c npx -a -y session-forge
// mcp.json
{
  "mcpServers": {
    "420247jake-session-forge": {
      "command": "npx",
      "args": [
        "-y",
        "session-forge"
      ]
    }
  }
}
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 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.77 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 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.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 9 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/session-forge@2.0.3

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 →

Dependencies 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 15 exposed · ~1,298 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
data_delete ~86

Delete a specific entry from a data store by its index from data_list. Returns the deleted entry for confirmation.

NameTypeReqDescription
entry_indexnumberyes1-based index of the entry to delete (from data_list output)
querystringIf data_list was filtered by query, provide the same query so indexes match
storestringyesWhich store to delete from

No output schema declared.

No examples provided.

data_list ~70

List stored entries in a data store. Returns numbered summaries for browsing. Use with data_delete to remove specific entries.

NameTypeReqDescription
limitnumberMax entries to return (default 10)
querystringOptional search filter to narrow results
storestringyesWhich store to list

No output schema declared.

No examples provided.

data_manage ~98

Manage session-forge data. Actions: prune (remove entries older than N days), export (dump all data as JSON), clear (wipe a specific store), stats (show entry counts and file sizes).

NameTypeReqDescription
actionstringyesAction to perform
daysnumberFor prune: remove entries older than this many days (default: 90)
storestringWhich data store to act on (default: all)

No output schema declared.

No examples provided.

dead_end_record ~114

Record a debugging dead end so we don't repeat it. Captures what was tried and why it failed.

NameTypeReqDescription
attemptedstringyesWhat was tried
files_involvedarrayFiles involved
led_to_decisionstringTimestamp of the decision this dead end led to
lessonstringWhat to remember for next time
projectstringWhich project
tagsarrayTags for searching
why_failedstringyesWhy it didn't work

No output schema declared.

No examples provided.

dead_end_search ~95

Search past dead ends to avoid repeating mistakes

NameTypeReqDescription
fuzzybooleanEnable fuzzy matching for typos (default: true)
limitnumberMax results to return (default 20)
modestringSearch mode: 'and' requires all words, 'or' matches any (default: or)
querystringyesSearch term
tagsarrayFilter by tags

No output schema declared.

No examples provided.

decision_record ~117

Record a significant decision made during development. Helps future sessions understand why choices were made.

NameTypeReqDescription
alternativesarrayWhat other options existed
choicestringyesWhat was decided
outcomestringHow it turned out (can be updated later)
projectstringWhich project this relates to
reasoningstringyesWhy this choice was made
related_dead_endsarrayTimestamps of dead ends that led to this decision
tagsarrayTags for searching later

No output schema declared.

No examples provided.

decision_search ~98

Search past decisions to understand why things are the way they are

NameTypeReqDescription
fuzzybooleanEnable fuzzy matching for typos (default: true)
limitnumberMax results to return (default 20)
modestringSearch mode: 'and' requires all words, 'or' matches any (default: or)
querystringyesSearch term
tagsarrayFilter by tags

No output schema declared.

No examples provided.

full_context_recall ~72

Get EVERYTHING - user profile, recent sessions, decisions, dead ends. Use when starting fresh to get full context.

NameTypeReqDescription
memory_md_pathstringAbsolute path to MEMORY.md file to include in context and check for sync suggestions
projectstringFilter decisions and dead ends by project name

No output schema declared.

No examples provided.

journal_entry ~134

Record a session journal entry capturing the journey, not just the task. Call at END of meaningful sessions to preserve context.

NameTypeReqDescription
breakthroughsarrayWhat clicked or worked unexpectedly well
collaboration_notesstringNotes about working together - user preferences observed, rapport
emotional_contextstringHow did the session feel? User concerns, celebrations, frustrations
frustrationsarrayWhat was difficult or annoying
key_momentsarraySignificant moments - breakthroughs, realizations, fun exchanges
summarystringyesWhat happened this session (conversational, not just technical)

No output schema declared.

No examples provided.

journal_recall ~44

Retrieve recent session context and journeys. Call at START of sessions to remember the relationship.

NameTypeReqDescription
sessions_countnumberHow many recent sessions to retrieve (default 3)

No output schema declared.

No examples provided.

profile_get ~14

Get the current user profile

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

profile_update ~95

Update user profile with preferences, notes, or project info. Call when learning something about the user.

NameTypeReqDescription
add_notestringAdd a note about the user (observations, preferences)
add_projectstringAdd a project name to user's project list
namestringUser's name if learned
preferencesobjectPreferences like {communication_style, emoji_usage, technical_level, verbosity}

No output schema declared.

No examples provided.

session_checkpoint ~198

Save current session state. Call this every 3-5 tool calls to protect against UI crashes. Required: task, intent, next_steps

NameTypeReqDescription
contextobjectAny important state/variables
dead_ends_hitarrayTimestamps of dead ends recorded this session
decisions_madearrayTimestamps of decisions recorded this session
errors_encounteredarrayExact error messages hit during this session
files_touchedarrayFile paths modified
intentstringyesWhat you are trying to accomplish
key_findingsarrayImportant discoveries made during this session
next_stepsarrayyesPlanned next steps
recent_actionsarrayLast 3-5 actions
statusstringCurrent status
taskstringyesBrief task name
tool_call_countnumberApprox tool calls so far

No output schema declared.

No examples provided.

session_complete ~36

Mark the current session as complete. Call this when a task is finished.

NameTypeReqDescription
summarystringBrief summary of what was accomplished

No output schema declared.

No examples provided.

session_restore ~27

Check for interrupted work from a previous session. Call this FIRST at the start of any session.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the Session Forge MCP server?

Session Forge is an MCP server listed in the public MCP registry as io.github.420247jake/session-forge. Persistent memory and session intelligence for AI coding assistants. Zero config. This page covers its npm package (session-forge).

Is the Session Forge MCP server safe to use?

Session Forge scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting 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 Session Forge MCP server expose?

Session Forge exposes 15 tools: session_checkpoint, session_restore, session_complete, profile_get, profile_update, and 10 more. Their descriptions and schemas cost roughly 1,298 tokens of context every time the server is loaded.

Is the Session Forge MCP server still maintained?

Session Forge 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 Session Forge MCP server under?

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