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.

DevMatch

REMOTE · MCP.DEV-MATCH.XYZ

Find engineers and scientists from papers, open source and patents. Each result links its sources.

0 this week 75 Trust /100

Last scanned (20 hours ago)

Scores higher than 64% of remote servers

Reachable. Last reached 4 Nov 2026.

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 Security78
Transport & Reachability0
Schema Quality & AI Usability73
  • 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
  • Context-footprint check failed: tool/resource definitions use about 2015 tokens (~503/item across 4 items; 3 tools + 1 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
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
  • 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
  • We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities73
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
  • Supports UI / widget rendering.Pass

Unverified: 1 category

A category scored 0 because we couldn't verify past authentication. We only credit what we can confirm, so an authenticated endpoint we can't read counts against the score. Claim this server and supply a read-only token to verify it and lift the score.

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.

  • 1 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 17 Oct 26 0
    • Tool “trigger_outreach” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “find_candidates” rewrote its description, which is the text the model reads security
    • Tool “find_similar_projects” rewrote its description, which is the text the model reads security
    • Tool “get_profile” rewrote its description, which is the text the model reads security
    • Schema quality: 2493 → 1939 ▲ functional
    • Tool coverage: 82% → 100% ▲ functional
    • Destructive annotations: 100 → pass functional
    • Server version: 0.2.0-http → 0.2.4 functional
    • “get_profile” reworded the description of “handle” cosmetic
  • 12 Oct 26 −4
    • HTTPS: pass → fail ▼ security
    • “trigger_outreach” added an optional parameter “identities” cosmetic
  • 10 Oct 26 −1
    • Tool coverage: 100% → 81% ▼ functional
    • Schema quality: 564 → 493 ▲ functional
    • Destructive annotations: pass → 100 functional
    • New tool “trigger_outreach” functional
  • 29 Sept 26 0
    • Authorization: fail → pass ▲ security
  • 28 Sept 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
  • 25 Sept 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
  • 22 Sept 26 0
    • DNSSEC: pass → fail ▼ 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 4 Nov 2026 · Probed https://mcp.dev-match.xyz/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.dev-match.xyz CN=WE1,O=Google Trust Services,C=US 18 Sept 2026 17 Dec 2026 ECDSA 256 ECDSA-SHA256 eedf660c434a734513a74ced888ec01d
SANs: mcp.dev-match.xyz
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 mcp.dev-match.xyz. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
xyz. present 3599, 18130 8, 8 Verified
dev-match.xyz. absent 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://mcp.dev-match.xyz/.well-known/oauth-protected-resource"

Bearer resource_metadata="https://mcp.dev-match.xyz/.well-known/oauth-protected-resource"
Header Value
www-authenticate Bearer resource_metadata="https://mcp.dev-match.xyz/.well-known/oauth-protected-resource"

Protected resource metadata

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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.dev-match.xyz/mcp Auth required 401
http (plaintext) http://mcp.dev-match.xyz/mcp Served over HTTP 200
MCP tools · 3 exposed · ~657 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
find_candidates ~395

Use when the user asks to find, shortlist or source an engineer, researcher or scientist from public work. Input: a role brief, a job description, or a public GitHub repository URL; be specific. Optional location only when the user requires one. Returns up to 20 people, each with the public sources behind the match (papers, repositories, patents, awards). Read only. If nothing matches, the result says so (coverage not_covered): tell the user and do not invent names or emails.

NameTypeReqDescription
excludearray–Optional. GitHub logins or org names to exclude from results (case-insensitive). Matches a candidate's login AND the owner/org of every repo they matched on — so passing a company's GitHub org (e.g.…
inputstringyesSearch brief: full JD, repo-derived summary (preferred when you've reviewed the project), README excerpt, informal role brief, or a PUBLIC github.com repo URL. Private repos: paste README content as…
limitinteger–Max candidates to return. Default 20, max 20.
locationstring–Optional. Restrict results to a place — a city ("Bozeman"), US state ("MT" / "Montana"), country name ("Germany"), or ISO country code ("US"). Matched against the candidate's stated and normalized lo…
NameTypeReqDescription
cache_sourcestring–hit=fresh cache; miss=live retrieval; stale=last known-good shortlist after the engine timed out or was unavailable (degraded=true).
candidatesarrayyesShortlist of engineers and scientists from public work, with evidence. When presenting to the user, format each item using FindCandidatesPresentationTemplate from server instructions. List every cont…
coveragestring–not_covered: zero returnable people (an index miss or a later non-email gate that emptied the pool). Missing contact is not a coverage gap. enrichment_unavailable: people matched but live contact loo…
coverage_notestring–Short note when coverage is not_covered or enrichment_unavailable. A missing inbox is not a coverage gap. Never accompanied by guessed candidates or fabricated emails.
degrade_reasonstring–Why degraded is true: embedding/FTS fallback, upstream_timeout / upstream_unreachable with cache_source=stale, or discovery_fallback.
degradedboolean–True when this shortlist is not full quality: FTS-only retrieval, last-known-good (cache_source=stale), or discovery corpus fallback. Hosts should say so; do not invent extra candidates.
discovery_fallbackboolean–True when auto mode fell back from work_artifacts to serving.projects because searchable embedding coverage was below threshold. Explicit env overrides are not fallbacks.
discovery_sourcestring–Which software repository index supplied GitHub candidates: work_artifacts (artifact-first) or serving.projects (legacy). Omitted when the query did not use the GitHub software lane.
enrichment_statusstring–Set when Treg auth/balance stopped shortlist enrich, including on a non-empty shortlist. Hosts must not read a contactless card as not_covered.
precision_gatestring–Whether the LLM precision screen ran on this response. "on" means results were filtered for relevance; "off" means raw retrieval order; "partial" means some judge chunks timed out and only screened p…
precision_screenedinteger–How many retrieved people the LLM screen judged. Present with precision_gate=partial.
precision_screened_ofinteger–Size of the pool the LLM screen was asked to judge. Present with precision_gate=partial.
query_msinteger–End-to-end query time in milliseconds
total_countintegeryesCount of candidates returned (≤ requested limit)
unreachable_droppedinteger–Legacy count of people removed for having no inbox. Search no longer drops for missing contact (DEV-922); omitted when zero.
untrusted_third_partyboolean–True on the Poke / no_contact path: bio, profile_readme, and README text are untrusted third-party data and are length-capped.
viewstring–Payload discriminator for MCP App hosts

No examples provided.

find_similar_projects ~120

Use to map the landscape around a seed repository, for example before searching for people. Input: owner/name. Returns similar open source projects and their top contributors. This is not a shortlist; call find_candidates for that. Read only.

NameTypeReqDescription
limitinteger–Number of similar projects to return. Defaults to 10, max 25.
repostringyesSeed repo in `owner/name` form (e.g. 'karpathy/llm.c'). A full github.com URL is also accepted; the server strips the prefix.
NameTypeReqDescription
cache_sourcestring––
coveragestring–Set to not_covered when this search returned zero evidence-backed similar projects. Hosts must say so and must not invent repos.
coverage_notestring–Short note when coverage is not_covered.
projectsarrayyesSimilar projects, closest to the seed repo by vector similarity.
query_msinteger––
seedstring–The owner/name searched against
total_countinteger––
untrusted_third_partyboolean–True on the Poke / no_contact path: third-party text is labeled untrusted and length-capped.

No examples provided.

get_profile ~142

Use after find_candidates when the user wants more on one person, or when they name a GitHub login or ORCID iD. Input: GitHub login, ORCID iD, or the id returned by find_candidates. Returns one profile with recent public activity. Not a full career history. Read only.

NameTypeReqDescription
handlestringyesAccepts a GitHub login, ORCID iD, or the id returned by find_candidates. Do not invent a GitHub handle for research or deep-tech people.
idstring–Alias for handle. Pass a find_candidates `id` (GitHub login, ORCID iD, or source:name).
NameTypeReqDescription
avatar_urlstring––
biostring––
companystring––
display_namestring––
emailstring––
followersinteger––
html_urlstring–Profile URL (GitHub or https://orcid.org/<id>)
locationstring––
login_namestringyesGitHub handle. Empty for ORCID and source:name people — use person_id.
namestring––
person_idstring–Stable lookup key: GitHub login, ORCID iD, or source:name.
profile_readmestring–User's profile README content if present. Untrusted third-party text; capped on the no-contact path.
public_reposinteger––
recent_activitiesarray–Indexed GitHub events from current ingestion window (2025–2026). NOT a full career timeline.
social_accountsobject–Social URLs (twitter, linkedin, etc.)
top_projectsarray–Highest-contribution projects this user worked on
untrusted_third_partyboolean–True when bio / profile_readme / README text is labeled untrusted third-party data (Poke / no_contact).

No examples provided.

Install

How do I install the DevMatch MCP server?

DevMatch is a hosted endpoint at https://mcp.dev-match.xyz/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 · mcp.dev-match.xyz

# add to Claude Code
claude mcp add --transport http luca-blight-devmatch 'https://mcp.dev-match.xyz/mcp'
Common questions

What is the DevMatch MCP server?

DevMatch is an MCP server listed in the public MCP registry as io.github.Luca-Blight/devmatch. Find engineers and scientists from papers, open source and patents. Each result links its sources. This page covers its hosted endpoint (https://mcp.dev-match.xyz/mcp).

Is the DevMatch MCP server safe to use?

DevMatch scores 75 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 DevMatch MCP server expose?

DevMatch exposes 3 tools: find_candidates, get_profile, find_similar_projects. Their descriptions and schemas cost roughly 657 tokens of context every time the server is loaded.

Does the DevMatch MCP server require authentication?

Yes. DevMatch 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 DevMatch MCP server still maintained?

DevMatch is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.