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.

Palim

REMOTE · API.USEPALIM.COM

Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.

Available components

−56 this week 39 Trust /100

Last scanned (34 minutes ago)

Scores higher than 35% of remote servers

Reachable. Last reached 22 Nov 2026.

Category Memory and Knowledge

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security97
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema blocked by authentication: the endpoint requires auth we don't have to read it. See how to fix → Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Tool Safety0
  • Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Capabilities0
  • Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. See how to fix → Unverified

Unverified: 6 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm. Claim this server and supply a read-only token to verify it and lift the score.

What we tested

Checks we ran (5)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC

Checks we could not complete (6)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Transport in Transport & Reachability (scores 0 for this)Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
  • Schema quality in Schema Quality & AI Usability (scores 0 for this)Schema blocked by authentication: the endpoint requires auth we don't have to read it.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
  • Tool coverage in Tool Coverage (scores 0 for this)Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
  • Tool safety in Tool Safety (scores 0 for this)Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
  • Capabilities in Capabilities (scores 0 for this)Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

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.

  • 17 Nov 26 −56
    • Endpoint reachability: reachable → behind authorisation ▼ security
    • Stability: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Transport: pass → unverified ▼ security
    • Authorization: The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata. security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: 100 → unverified ▼ functional
  • 12 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “palim_checkpoint” rewrote its description, which is the text the model reads security
    • Tool “palim_resume” rewrote its description, which is the text the model reads security
    • Tool “palim_save_context” rewrote its description, which is the text the model reads security
    • Tool “palim_save_session” rewrote its description, which is the text the model reads security
    • “palim_checkpoint” reworded the description of “continues_from” cosmetic
    • “palim_save_context” reworded the description of “continues_from” cosmetic
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 5 Nov 26 0
    • “palim_search” reworded the description of “query” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 21 Oct 26 0
    • “palim_checkpoint” reworded the description of “tool_source” cosmetic
    • “palim_save_context” reworded the description of “tool_source” cosmetic
    • “palim_checkpoint” made “tool_source” optional cosmetic
    • “palim_save_context” made “tool_source” optional cosmetic

    4 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.

  • 17 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 3 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “palim_save_session” rewrote its description, which is the text the model reads security
    • Tool “palim_save_session” is now declared destructive security
  • 30 Sept 26 0
    • Stability: fail → 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 22 Nov 2026 · Probed https://api.usepalim.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.usepalim.com CN=WE1,O=Google Trust Services,C=US 26 Oct 2026 24 Jan 2027 ECDSA 256 ECDSA-SHA256 b0c8132c499614690eabcb8594878752
SANs: api.usepalim.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.usepalim.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
usepalim.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On connection
HTTP status 401

WWW-Authenticate challenge Bearer resource_metadata="https://api.usepalim.com/.well-known/oauth-protected-resource/mcp"

Bearer resource_metadata="https://api.usepalim.com/.well-known/oauth-protected-resource/mcp"
Header Value
strict-transport-security max-age=31536000; includeSubDomains
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
www-authenticate Bearer resource_metadata="https://api.usepalim.com/.well-known/oauth-protected-resource/mcp"

Protected resource metadata

Document https://api.usepalim.com/.well-known/oauth-protected-resource/mcp
Retrieved Yes
Resource https://api.usepalim.com/mcp
Authorisation server https://api.usepalim.com

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.usepalim.com/mcp Auth required 401
http (plaintext) http://api.usepalim.com/mcp HTTPS enforced 301 https://api.usepalim.com/mcp
MCP tools · 11 exposed · ~1,601 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
palim_add_memory ~79

Store a memory, fact, decision, or preference for later retrieval.

NameTypeReqDescription
contentstringyesContent of the memory
metadataobject–Additional metadata
source_session_idstring–Optional reference to source session
tagsarray–Tags for categorization
typestringyesType of memory
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_checkpoint ~307

Saves a short handoff of the current chat: goal, state, decisions and open items, without the transcript. Saving again with the same session_id updates the same entry.

NameTypeReqDescription
contextstringyesHandoff another AI can continue from: goal, state, constraints, next steps.
continues_fromstring–Optional session_id of the thread this chat continues.
created_atstring–Optional ISO 8601 chat date from the client.
decisions_madearray–Decisions in this chat.
key_topicsarray–Main topics.
open_itemsarray–Open tasks.
originstring–human (default) or automation (hooks/cron).
projectstring–Optional project name.
referenced_filesarray–Relevant files.
resolved_open_itemsarray–Previously open items that are now done; quote a leading fragment.
session_idstring–Stable chat ID. Reuse it so checkpoints update one row. Claude Code/Codex: claude-code-<client session id>.
source_urlsarray–Optional URLs.
statusstring–Optional status, e.g. laufend or abgeschlossen.
tagsarray–Optional search tags.
titlestring–Chat title when visible.
tool_sourcestring–Client: cursor, claude, chatgpt, … Optional; defaults from the MCP client name, else unknown.
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_delete_memory ~48

Permanently delete one stored memory by ID. Use for user-requested cleanup or deletion; this cannot be undone.

NameTypeReqDescription
memory_idstringyesID of the memory to permanently delete
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_delete_session ~66

Delete a chat session. Soft delete by default (reversible). Use hard_delete=true for permanent deletion.

NameTypeReqDescription
hard_deleteboolean–If true, permanently deletes all data. Default: false (soft delete).
session_idstringyesThe session ID to delete
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_get_brain ~96

Distilled knowledge profile. No args: recent topic index (capped). With topic: full document. Pass limit for a larger or full index.

NameTypeReqDescription
limitnumber–Max topics in the index (most recently updated first). Default 20 when omitted. Pass 0 for every topic.
topicstring–Optional topic slug or name. When set, returns the full topic document instead of the index.
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_get_context ~103

Get formatted context for a specific topic by searching and retrieving relevant sessions.

NameTypeReqDescription
max_sessionsnumber–Maximum number of sessions to include (default: 3)
projectstring–Optional filter by project
statusstring–Optional filter by metadata.status (e.g. "laufend", "abgeschlossen").
tagsarray–Filter by metadata tags (match any).
topicstringyesTopic to get context for.
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_help ~36

Show an overview of all available Palim tools and usage instructions.

NameTypeReqDescription
categorystring–Filter by category. Default: all.
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_resume ~164

Returns the user's most recently updated Palim thread as a handoff: state, decisions and open items. Useful at the start of a new chat; the thread may be unrelated to the current request. Project filter is case-insensitive.

NameTypeReqDescription
include_messagesboolean–Optional: append the tail of the transcript when the thread has stored messages. Default false.
projectstring–Optional: only consider threads belonging to this project (case-insensitive; Logisoft ≡ logisoft).
tool_sourcestring–Optional: only consider threads from one client (cursor, claude, codex, chatgpt, ...).
within_hoursnumber–Optional: ignore threads older than this many hours. Omit to always return the latest thread.
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_save_context ~299

Saves a self-contained handoff of the current chat without the transcript. Saving again with the same session_id updates the same entry.

NameTypeReqDescription
contextstringyesHandoff another AI can continue from: goal, state, constraints, next steps.
continues_fromstring–Optional session_id of the thread this chat continues.
created_atstring–Optional ISO 8601 chat date from the client.
decisions_madearray–Decisions in this chat.
key_topicsarray–Main topics.
open_itemsarray–Open tasks.
originstring–human (default) or automation (hooks/cron).
projectstring–Optional project name.
referenced_filesarray–Relevant files.
resolved_open_itemsarray–Previously open items that are now done; quote a leading fragment.
session_idstring–Stable chat ID. Reuse it so checkpoints update one row. Claude Code/Codex: claude-code-<client session id>.
source_urlsarray–Optional URLs.
statusstring–Optional status, e.g. laufend or abgeschlossen.
tagsarray–Optional search tags.
titlestring–Chat title when visible.
tool_sourcestring–Client: cursor, claude, chatgpt, … Optional; defaults from the MCP client name, else unknown.
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_save_session ~215

Saves or appends a full chat transcript with its summary. Not for personal data of children under 16 (or a higher local consent age), HIPAA PHI, PCI payment card data or adult content. Appending with the same session_id adds the new messages to the existing session.

NameTypeReqDescription
created_atstring–Optional ISO 8601 creation date from the AI client (new sessions only).
messagesarrayyesMessages to save (role + content). When appending, only unsaved messages.
metadataobject–Session metadata. tool_source is required.
overwriteboolean–Replace all existing messages instead of appending. Default: false.
session_idstring–Session id. Reuse across saves in this chat; else from chat URL or a new UUID.
summaryobject–Full-conversation summary. Required arrays may be empty.
titlestringyesSession title. Reuse across saves; else the exact chat title from the client UI.
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

palim_search ~188

Search saved sessions and memories. Query matches session text or memory content/id. Supports metadata filtering via tags/project/status/tool_source. Omit query for tags-only or project-only session filtering. Project match is case-insensitive.

NameTypeReqDescription
limitnumber–Maximum number of results (default: 5)
projectstring–Optional case-insensitive project filter (Logisoft ≡ logisoft). Allowed without query or tags.
querystring–Keyword search query. Omit for tags-only or project-only filtering.
statusstring–Optional filter by metadata.status (e.g. "laufend", "abgeschlossen", "referenz", "archiviert").
tagsarray–Filter by metadata tags (match any).
tool_sourcestring–Optional explicit filter by tool source (cursor, claude, chatgpt, web, etc.).
NameTypeReqDescription
messagestringyesHuman-readable tool result text.

No examples provided.

Install

How do I install the Palim MCP server?

Palim is a hosted endpoint at https://api.usepalim.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.usepalim.com

# add to Claude Code
claude mcp add --transport http joleschmidt-palim 'https://api.usepalim.com/mcp'
Common questions

What is the Palim MCP server?

Palim is an MCP server listed in the public MCP registry as io.github.joleschmidt/palim. Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS. This page covers its hosted endpoint (https://api.usepalim.com/mcp).

Is the Palim MCP server safe to use?

Palim scores 39 out of 100 on VerifyMCP. 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 Palim MCP server expose?

Palim exposes 11 tools: palim_resume, palim_checkpoint, palim_save_context, palim_save_session, palim_get_context, and 6 more. Their descriptions and schemas cost roughly 1,601 tokens of context every time the server is loaded.

Does the Palim MCP server require authentication?

Yes. Palim asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Palim MCP server still maintained?

Palim is still listed as active in the MCP registry. We last reached this channel on 22 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Palim MCP server?

VerifyMCP ran 5 checks on Palim, covering TLS certificate, Authorization, HTTPS, HSTS header and 1 more. 6 items could not be completed, a gap on our side rather than a finding about Palim: Transport, Schema quality, Stability, Tool coverage and 2 more. 6 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.