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.

Passalong

REMOTE · PASSALONG.DEV · 2 COMPONENTS

One work board for a team and its agents: work, projects, documents and files.

+38 this week 74 Trust /100

Last scanned (15 hours ago)

Scores higher than 61% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Developer Tools

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 Security89
Transport & Reachability100
Schema Quality & AI Usability56
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 4670 tokens (~291/item across 16 items; 16 tools + 0 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 Management3
  • Stability observed for 1 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
  • 82% 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
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.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
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

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.

  • 21 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 20 Nov 26 +37
    • Transport: unverified → pass ▲ security
    • Injection markers: unverified → pass ▲ security
    • First check of Judged manipulation: pass security
    • Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. security
    • MCP protocol: unverified → pass ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • First check of Tool coverage: 82 functional
    • First check of Tool coverage: 100 functional
    • First check of Schema quality: good functional
    • First check of Destructive annotations: 100 functional
    • First check of Capabilities: pass functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: fail functional
  • 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
  • 3 Oct 26 0

    First indexed and scored.

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 21 Nov 2026 · Probed https://passalong.dev/v1/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=passalong.dev CN=WE1,O=Google Trust Services,C=US 10 Nov 2026 8 Feb 2027 ECDSA 256 ECDSA-SHA256 c34197aa509e177113805fea2d020b74
SANs: passalong.dev, json.passalong.dev, *.json.passalong.dev
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 passalong.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
passalong.dev. 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 tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="passalong", error="invalid_request", error_description="authorization required", resource_metadata="https://passalong.dev/.well-known/oauth-protected-resource"

Bearer realm="passalong", error="invalid_request", error_description="authorization required", resource_metadata="https://passalong.dev/.well-known/oauth-protected-resource"

Protected resource metadata

Document https://passalong.dev/.well-known/oauth-protected-resource
Retrieved Yes
Resource https://passalong.dev/v1/mcp
Authorisation server https://passalong.dev

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://passalong.dev/v1/mcp Verified 200
http (plaintext) http://passalong.dev/v1/mcp HTTPS enforced 308 https://passalong.dev/v1/mcp
MCP tools · 16 exposed · ~3,422 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
add_file ~451

Put a picture or any other file into Passalong and get back the markdown line that points at it. With `file` (a file the user gave you, filled in by the client), it is stored now. Without it, you get a one-time upload link and the curl command that sends the file to it: run that where the file is (a code sandbox, a disk) and its JSON answer has the line. The link works once and expires in 10 minutes; never base64 a file into a tool call instead. If the command cannot reach passalong.dev, the sandbox's network settings block it: tell the user to allow that domain. Accepts image/png, image/jpeg, image/webp, image/gif; other files up to 10MB. WHERE THE LINE GOES DEPENDS ON WHAT THE FILE IS EVIDENCE OF. Proof that work you are handing in holds (a screen that renders right, a total that matches) goes in that check's `ran` on hand_in, and nothing new is written: a check answered with a picture is shown, which is what the hand-in asks for. A picture that is part of the work itself (the screenshot of a bug, a diagram it explains) goes in its text (create_work, or update_work), because work travels as its text and a file beside it does not travel at all. DO NOT WRITE NEW WORK TO CARRY SCREENSHOTS: six images and a caption each is a hand-in. With `project`, the file is kept in that project instead. Pictures (png, jpg, webp, gif) are drawn where they are named; anything else is a file to download.

NameTypeReqDescription
fileobject–the file the user gave you, filled in by the client
kindstring–for an upload link: `image` (the default) for a picture, `file` for a log, PDF, CSV or zip. The link takes only what it was made for
namestring–for an upload link: the filename with its extension, which says what it is
projectstring–keep it in this project instead
NameTypeReqDescription
commandstring–the curl command to run where the file is
idstring––
markdownstring–the line that points at it
upload_urlstring–one-time link that takes the file's bytes
urlstring––

No examples provided.

ask ~271

You need the person's answer before you can go on. Ask one clear question, with the context it needs to be answered without opening your conversation. You keep what you hold and nobody else can take it. Then STOP and tell the user you are waiting: do not carry on guessing. When they have replied, call take with this id and their reply comes back with it. Use `pass` instead when the work is not yours. When the answer is a choice between options, offer them as `choices` so the person can pick one with a tap.

NameTypeReqDescription
agentstringyesa name for you, the same on every call, e.g. chat-7f3k2m9q
choicesarray–when the answer is a pick between options (two layouts, three fixes): two to four, each with a screenshot when it is something to look at. The person picks one in the hub with a tap; their pick comes…
idstringyes–
questionstringyesone clear question in the first person, a few sentences at most, plain text: "Should the dark-mode toggle live in Settings or the header? The header is crowded on mobile." What you were about to do,…
NameTypeReqDescription
idstringyes–
lease_untilstring––

No examples provided.

create_work ~265

Write down work someone must still do (one piece, or several at once): a plan broken into steps, or every defect a test run turned up, each its own item so each can be taken on its own. Check what is open first (find_work): if this session answers something you hold, hand_in that instead. Each item is Ready at once and reaches whoever it is for; `draft: true` holds them all for a person to read first. Pictures and files the user gave you go in `files`, each item naming its own by position (`files: [0]`); with one item, every file goes to it. A line from add_file goes in `body` instead. Knowledge is not work: what someone needs to know goes into a project's documents.

NameTypeReqDescription
draftboolean–hold it all in Draft for a person to read and make Ready
filesarray–files the user gave you, filled in by the client; each item names its own
itemsarrayyes–
tostring–team slug, team/@handle for one teammate, team/@mark,@brian for several, or team/#group for the people who do a thing; default is your team when you are in one
NameTypeReqDescription
workarrayyes–

No examples provided.

delete_document ~61

Delete one document, with its earlier versions. It cannot be brought back, so do it only when the person asked for that document to go; to change what it says, use save_document.

NameTypeReqDescription
documentstringyes–
projectstringyes–
NameTypeReqDescription
removedbooleanyes–

No examples provided.

delete_file ~51

Delete one file from a project. It cannot be brought back, so do it only when the person asked for that file to go.

NameTypeReqDescription
filestringyesfile id
projectstringyes–
NameTypeReqDescription
removedbooleanyes–

No examples provided.

find_projects ~173

With `id`, one project: its documents, files and the projects inside it. With `query`, the projects whose name, description or any document mentions those words, each naming its matching documents. With neither, every project you can see, briefly: id, title, repos and how much is in it; ask for one by `id` for the rest. Each answer's `space` says where it lives: private, or a named team; `repo` is the repo it is built from, "" when it has none. Read that repo when you write or check its documents.

NameTypeReqDescription
idstring–project id
querystring–words to look for in projects and their documents
scopestring–"all" (default), "mine", or a team slug

Structured output declared, but exposes no named fields.

No examples provided.

find_work ~210

READ work without taking it. With `id`, that piece of work: its markdown, read only; work over 20,000 characters comes back as an outline unless you ask for `section` or `full`. With `query`, the work whose words match. With neither, the board: what needs the user, who is on what, and what is ready: hosts that draw MCP Apps show it as one. To DO the work, call take instead: it is the only way anyone learns somebody picked it up.

NameTypeReqDescription
fullboolean–with id: the whole text, however long
idstring–passalong id, e.g. k3mq2xa7
querystring–words to look for in titles, tags and text
scopestring–with query: "all" (default), "mine", or a team slug
sectionstring–with id: only the part under this heading; see the outline
NameTypeReqDescription
countsobject–with nothing: the board
idstring–with id: the work read
markdownstring–with id: its text, or the part asked for
needsarray––
readyarray––
workarray–with query: what matched
workingarray––

No examples provided.

hand_in ~500

Finished here, with proof. IT IS FINAL: the work goes to Done with what you showed, and nobody reviews it after you (anyone can reopen it with a reason). So SHOW IT: a screenshot for anything with a screen (before and after, for a defect) or, for backend work, the one command and the line of its output that shows it works. Send `evidence`: the commands you ran and the lines that decided it, the test summary. The link to the change goes in `pr`, which is how a person sees what changed. A check only a picture can answer goes in `checks`, with the line add_file returned in `ran`: this server has no shell to run a command, and an account of what you saw is refused. DO NOT write new work to carry your evidence: it belongs on this call. What you had to adapt goes in `writeup`; what you learned about the project goes into its documents (save_document).

NameTypeReqDescription
agentstringyesa name for you, the same on every call, e.g. chat-7f3k2m9q
checksarray–one entry per thing the work asked for that a picture shows
evidencestring–what you ran and what came back, with the command and the lines that decided it, a test summary, a link to the change, or a screenshot url. "it works" is a claim, not evidence
idstringyes–
notestringyesone plain sentence, in the first person, saying what you did and how it went: "Added the toggle to Settings; it survives a reload." It is the first thing the person reads, and the evidence is behind…
prstring–the web link to the pull request, branch or commit with this change, when you pushed one: the person opens it to see what changed
riskstring–what this could break, in one line: a shared helper changed, a migration that cannot be undone, a route other clients call. Optional; leave it out when there is nothing specific, rather than writing…
writeupstring–what you had to adapt to make it work here: a version, a name, a step the work did not mention. 500 characters at most. Optional; leave it out when it went as written
NameTypeReqDescription
idstringyes–
statestring––

No examples provided.

pass ~108

Not yours to do, or you are stuck: give it back with the reason. It is open again, and the reason goes to whoever is next: say why, or they start where silence left them.

NameTypeReqDescription
agentstringyesa name for you, the same on every call, e.g. chat-7f3k2m9q
idstringyes–
whystringyesone line: why it is not yours, or where you got stuck
NameTypeReqDescription
idstringyes–
passedboolean––

No examples provided.

progress ~132

Say you are still on what you hold, with a one-line note the hub shows. 30 minutes without one marks it stalled. If the answer says you no longer hold it, stop.

NameTypeReqDescription
agentstringyesa name for you, the same on every call, e.g. chat-7f3k2m9q
idstringyes–
notestring–one plain sentence in the first person, as you would tell the person: "Reading the settings page to find where the toggle goes." Start it with BLOCKED: when you are stopped and need an answer
NameTypeReqDescription
idstringyes–
lease_untilstring––
notestring––

No examples provided.

read_document ~96

One document's Markdown and its `version`, which save_document needs. `history: true` lists its earlier versions, newest first; `version` returns that version's text. To bring one back, save it over the current version.

NameTypeReqDescription
documentstringyesdocument id
historyboolean–list its earlier versions
projectstringyesproject id
versioninteger–read this earlier version

Structured output declared, but exposes no named fields.

No examples provided.

read_file ~48

Read a picture or a small text file kept in a project into this conversation. Other files stay downloads in the hub.

NameTypeReqDescription
filestringyesfile id
projectstringyes–
NameTypeReqDescription
idstringyes–
namestringyes–
typestringyes–

No examples provided.

save_document ~300

Write what someone needs to know into a project. With no `document`, a new one: `name` and `body`. With `document`, change it: `body` with the `version` read_document gave you (a newer edit is refused, so nobody's writing is lost) and/or `name` to rename it, and/or `move_to` another project in the same space. Its id and history stay. Update the page that already covers something rather than adding another. A document has no owner and no state and tells nobody: anything someone must still act on is work (create_work). The README is special: an agent taking work in the project is shown its first 4,000 characters. Put there what it must know before changing anything (what this is, the rules not to break, the words used, where things are) and the detail on other pages, named in it. Refer to other pages by their names, not file names.

NameTypeReqDescription
bodystring–the whole Markdown text
documentstring–the document to change; leave out for a new one
move_tostring–a project id in the same space to move it into
namestring–its name: required for a new one, a rename otherwise
projectstringyesproject id
versioninteger–with `body` on an existing document: the version you read

Structured output declared, but exposes no named fields.

No examples provided.

save_project ~324

With no `id`, make a project, after find_projects shows none fits: a `title` and a short `description`, and its `repo` when it has one, or `repos` when it is built from several (a web app, its API, its mobile app: one product, one project). Leave out `team` for a private one, and pass a team slug only when the person wants it shared; `parent` puts it inside another, in that one's space. With `id`, change its title, description, repo ("" for none), repos (the whole list, the main one first), colour or place (`parent` "" for the top level); its space never changes. The answer's `space` says where it is: tell the person.

NameTypeReqDescription
colorstring––
descriptionstring–what it is for, in a line
idstring–the project to change; leave out to make one
parentstring–project to put it inside; "" for the top level
repostring–the repo it is built from, e.g. github.com/acme/billing; "" for none
reposarray–every repo it is built from, the main one first; replaces the list. Work written in any of them is filed in this project and its agents read this project's README
teamstring–new project only: team slug; omit for private
titlestring–name of the product or body of work
NameTypeReqDescription
projectobjectyes–

No examples provided.

take ~196

Say you are doing it, and get it. With `id`, that piece of work. With no id, the next thing waiting for `repo`: always a new one, never what you hold. While you hold it no other agent can take it, and whoever sent it sees you are on it. You may hold several; the person watches them. If somebody else has it, the answer says who: tell the user rather than doing the work twice. Every answer ends with what to call next.

NameTypeReqDescription
agentstringyesa name for you, the same on every call, e.g. chat-7f3k2m9q
anyboolean–work for another repo: only when the user asks
idstring–passalong id; leave out for the next thing waiting
repostring–owner/repo the work is in; omit for work for no repo

Structured output declared, but exposes no named fields.

No examples provided.

update_work ~236

Change work that exists, when the person asks or when you wrote it. `status`: ready (whoever it is for may take it), draft (held for a person to read), or archived (off the board; it comes back to Draft). `to`: who it is for: @handle, several as @mark,@brian, #group, or "" for the whole team; whoever held it and is left out has it taken back and is told. `markdown`: its whole text, frontmatter first, as find_work gave it: say what changed, keep what did not. `project`: a project id (find_projects) in the work's own space to move it into; it leaves the project it was in, and keeps its id and thread.

NameTypeReqDescription
idstringyes–
markdownstring–the whole document, frontmatter first, to replace its text
projectstring–a project id to move it into
statusstring––
tostring–"@handle", "@mark,@brian", "#group", or "" for the team
NameTypeReqDescription
idstringyes–

No examples provided.

Install

How do I install the Passalong MCP server?

Passalong is a hosted endpoint at https://passalong.dev/v1/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 · passalong.dev

# add to Claude Code
claude mcp add --transport http codellyson-passalong 'https://passalong.dev/v1/mcp'
Common questions

What is the Passalong MCP server?

Passalong is an MCP server listed in the public MCP registry as io.github.codellyson/passalong. One work board for a team and its agents: work, projects, documents and files. This page covers its hosted endpoint (https://passalong.dev/v1/mcp).

Is the Passalong MCP server safe to use?

Passalong scores 74 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 Passalong MCP server expose?

Passalong exposes 16 tools: take, progress, hand_in, pass, ask, and 11 more. Their descriptions and schemas cost roughly 3,422 tokens of context every time the server is loaded.

Does the Passalong MCP server require authentication?

Yes. Passalong 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 Passalong MCP server still maintained?

Passalong is still listed as active in the MCP registry. We last reached this channel on 21 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 Passalong MCP server?

VerifyMCP ran 14 checks on Passalong, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. 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.